Posts in category: Google AI

Read More

Posted by Jarrod McClean, Staff Research Scientist, Google Quantum AI, and Hsin-Yuan Huang, Graduate Student, Caltech

In efforts to learn about the quantum world, scientists face a big obstacle: their classical experience of the world. Whenever a quantum system is measured, the act of this measurement destroys the “quantumness” of the state. For example, if the quantum state is in a superposition of two locations, where it can seem to be in two places at the same time, once it is measured, it will randomly appear either ”here” or “there”, but not both. We only ever see the classical shadows cast by this strange quantum world.

A growing number of experiments are implementing machine learning (ML) algorithms to aid in analyzing data, but these have the same limitations as the people they aim to help: They can’t directly access and learn from quantum information. But what if there were a quantum machine learning algorithm that could directly interact with this quantum data?

In “Quantum Advantage in Learning from Experiments”, a collaboration with researchers at Caltech, Harvard, Berkeley, and Microsoft published in Science, we show that a quantum learning agent can perform exponentially better than a classical learning agent at many tasks. Using Google’s quantum computer, Sycamore, we demonstrate the tremendous advantage that a quantum machine learning (QML) algorithm has over the best possible classical algorithm. Unlike previous quantum advantage demonstrations, no advances in classical computing power could overcome this gap. This is the first demonstration of a provable exponential advantage in learning about quantum systems that is robust even on today’s noisy hardware.

Quantum Speedup
QML combines the best of both quantum computing and the lesser-known field of quantum sensing.

Quantum computers will likely offer exponential improvements over classical systems for certain problems, but to realize their potential, researchers first need to scale up the number of qubits and to improve quantum error correction. What’s more, the exponential speed-up over classical algorithms promised by quantum computers relies on a big, unproven assumption about so-called “complexity classes” of problems — namely, that the class of problems that can be solved on a quantum computer is larger than those that can be solved on a classical computer.. It seems like a reasonable assumption, and yet, no one has proven it. Until it’s proven, every claim of quantum advantage will come with an asterisk: that it can do better than any known classical algorithm.

Quantum sensors, on the other hand, are already being used for some high-precision measurements and offer modest (and proven) advantages over classical sensors. Some quantum sensors work by exploiting quantum correlations between particles to extract more information about a system than it otherwise could have. For example, scientists can use a collection of N atoms to measure aspects of the atoms’ environment like the surrounding magnetic fields. Typically the sensitivity to the field that the atoms can measure scales with the square root of N. But if one uses quantum entanglement to create a complex web of correlations between the atoms, then one can improve the scaling to be proportional to N. But as with most quantum sensing protocols, this quadratic speed-up over classical sensors is the best one can ever do.

Enter QML, a technology that straddles the line between quantum computers and quantum sensors. QML algorithms make computations that are aided by quantum data. Instead of measuring the quantum state, a quantum computer can store quantum data and implement a QML algorithm to process the data without collapsing it. And when this data is limited, a QML algorithm can squeeze exponentially more information out of each piece it receives when considering particular tasks.

Comparison of a classical machine learning algorithm and a quantum machine learning algorithm. The classical machine learning algorithm measures a quantum system, then performs classical computations on the classical data it acquires to learn about the system. The quantum machine learning algorithm, on the other hand, interacts with the quantum states produced by the system, giving it a quantum advantage over the CML.

To see how a QML algorithm works, it’s useful to contrast with a standard quantum experiment. If a scientist wants to learn about a quantum system, they might send in a quantum probe, such as an atom or other quantum object whose state is sensitive to the system of interest, let it interact with the system, then measure the probe. They can then design new experiments or make predictions based on the outcome of the measurements. Classical machine learning (CML) algorithms follow the same process using an ML model, but the operating principle is the same — it’s a classical device processing classical information.

A QML algorithm instead uses an artificial “quantum learner.” After the quantum learner sends in a probe to interact with the system, it can choose to store the quantum state rather than measure it. Herein lies the power of QML. It can collect multiple copies of these quantum probes, then entangle them to learn more about the system faster.

Suppose, for example, the system of interest produces a quantum superposition state probabilistically by sampling from some distribution of possible states. Each state is composed of n quantum bits, or qubits, where each is a superposition of “0” and “1” — all learners are allowed to know the generic form of the state, but must learn its details.

In a standard experiment, where only classical data is accessible, every measurement provides a snapshot of the distribution of quantum states, but since it’s only a sample, it is necessary to measure many copies of the state to reconstruct it. In fact, it will take on the order of 2ⁿ copies.

A QML agent is more clever. By saving a copy of the n-qubit state, then entangling it with the next copy that comes along, it can learn about the global quantum state more quickly, giving a better idea of what the state looks like sooner.

Basic schematic of the QML algorithm. Two copies of a quantum state are saved, then a “Bell measurement” is performed, where each pair is entangled and their correlations measured.

<!–

Basic schematic of the QML algorithm. Two copies of a quantum state are saved, then a “Bell measurement” is performed, where each pair is entangled and their correlations measured.

–>

The classical reconstruction is like trying to find an image hiding in a sea of noisy pixels — it could take a very long time to average-out all the noise to know what the image is representing. The quantum reconstruction, on the other hand, uses quantum mechanics to isolate the true image faster by looking for correlations between two different images at once.

Results
To better understand the power of QML, we first looked at three different learning tasks and theoretically proved that in each case, the quantum learning agent would do exponentially better than the classical learning agent. Each task was related to the example given above:

1. Learning about incompatible observables of the quantum state — i.e., observables that cannot be simultaneously known to arbitrary precision due to the Heisenberg uncertainty principle, like position and momentum. But we showed that this limit can be overcome by entangling multiple copies of a state.
2. Learning about the dominant components of the quantum state. When noise is present, it can disturb the quantum state. But typically the “principal component” — the part of the superposition with the highest probability — is robust to this noise, so we can still glean information about the original state by finding this dominant part.
3. Learning about a physical process that acts on a quantum system or probe. Sometimes the state itself is not the object of interest, but a physical process that evolves this state is. We can learn about various fields and interactions by analyzing the evolution of a state over time.

In addition to the theoretical work, we ran some proof-of-principle experiments on the Sycamore quantum processor. We started by implementing a QML algorithm to perform the first task. We fed an unknown quantum mixed state to the algorithm, then asked which of two observables of the state was larger. After training the neural network with simulation data, we found that the quantum learning agent needed exponentially fewer experiments to reach a prediction accuracy of 70% — equating to 10,000 times fewer measurements when the system size was 20 qubits. The total number of qubits used was 40 since two copies were stored at once.

Experimental comparison of QML vs. CML algorithms for predicting a quantum state’s observables. While the number of experiments needed to achieve 70% accuracy with a CML algorithm (“C” above) grows exponentially with the size of the quantum state n, the number of experiments the QML algorithm (“Q”) needs is only linear in n. The dashed line labeled “Rigorous LB (C)” represents the theoretical lower bound (LB) — the best possible performance — of a classical machine learning algorithm.

<!–

Experimental comparison of QML vs. CML algorithms for predicting a quantum state’s observables. While the number of experiments needed to achieve 70% accuracy with a CML algorithm (“C” above) grows exponentially with the size of the quantum state n, the number of experiments the QML algorithm (“Q”) needs is only linear in n. The dashed line labeled “Rigorous LB (C)” represents the theoretical lower bound (LB) — the best possible performance — of a classical machine learning algorithm.

–>

In a second experiment, relating to the task 3 above, we had the algorithm learn about the symmetry of an operator that evolves the quantum state of their qubits. In particular, if a quantum state might undergo evolution that is either totally random or random but also time-reversal symmetric, it can be difficult for a classical learner to tell the difference. In this task, the QML algorithm can separate the operators into two distinct categories, representing two different symmetry classes, while the CML algorithm fails outright. The QML algorithm was completely unsupervised, so this gives us hope that the approach could be used to discover new phenomena without needing to know the right answer beforehand.

Experimental comparison of QML vs. CML algorithms for predicting the symmetry class of an operator. While QML successfully separates the two symmetry classes, the CML fails to accomplish the task.

Conclusion
This experimental work represents the first demonstrated exponential advantage in quantum machine learning. And, distinct from a computational advantage, when limiting the number of samples from the quantum state, this type of quantum learning advantage cannot be challenged, even by unlimited classical computing resources.

So far, the technique has only been used in a contrived, “proof-of-principle” experiment, where the quantum state is deliberately produced and the researchers pretend not to know what it is. To use these techniques to make quantum-enhanced measurements in a real experiment, we’ll first need to work on current quantum sensor technology and methods to faithfully transfer quantum states to a quantum computer. But the fact that today’s quantum computers can already process this information to squeeze out an exponential advantage in learning bodes well for the future of quantum machine learning.

Acknowledgements
We would like to thank our Quantum Science Communicator Katherine McCormick for writing this blog post. Images reprinted with permission from Huang et al., Science, Vol 376:1182 (2022).

Read More

Posted by Sara Beery, Student Researcher, and Jonathan Huang, Research Scientist, Google Research, Perception Team

Over four billion people live in cities around the globe, and while most people interact daily with others — at the grocery store, on public transit, at work — they may take for granted their frequent interactions with the diverse plants and animals that comprise fragile urban ecosystems. Trees in cities, called urban forests, provide critical benefits for public health and wellbeing and will prove integral to urban climate adaptation. They filter air and water, capture stormwater runoff, sequester atmospheric carbon dioxide, and limit erosion and drought. Shade from urban trees reduces energy-expensive cooling costs and mitigates urban heat islands. In the US alone, urban forests cover 127M acres and produce ecosystem services valued at $18 billion. But as the climate changes these ecosystems are increasingly under threat.

Census data is typically not comprehensive, covering a subset of public trees and not including those in parks.

Urban forest monitoring — measuring the size, health, and species distribution of trees in cities over time — allows researchers and policymakers to (1) quantify ecosystem services, including air quality improvement, carbon sequestration, and benefits to public health; (2) track damage from extreme weather events; and (3) target planting to improve robustness to climate change, disease and infestation.

However, many cities lack even basic data about the location and species of their trees. Collecting such data via a tree census is costly (a recent Los Angeles census cost $2 million and took 18 months) and thus is typically conducted only by cities with substantial resources. Further, lack of access to urban greenery is a key aspect of urban social inequality, including socioeconomic and racial inequality. Urban forest monitoring enables the quantification of this inequality and the pursuit of its improvement, a key aspect of the environmental justice movement. But machine learning could dramatically lower tree census costs using a combination of street-level and aerial imagery. Such an automated system could democratize access to urban forest monitoring, especially for under-resourced cities that are already disproportionately affected by climate change. While there have been prior efforts to develop automated urban tree species recognition from aerial or street-level imagery, a major limitation has been a lack of large-scale labeled datasets.

Today we introduce the Auto Arborist Dataset, a multiview urban tree classification dataset that, at ~2.6 million trees and >320 genera, is two orders of magnitude larger than those in prior work. To build the dataset, we pulled from public tree censuses from 23 North American cities (shown above) and merged these records with Street View and overhead RGB imagery. As the first urban forest dataset to cover multiple cities, we analyze in detail how forest models can generalize with respect to geographic distribution shifts, crucial to building systems that scale. We are releasing all 2.6M tree records publicly, along with aerial and ground-level imagery for 1M trees.

The 23 cities in the dataset are spread across North America, and are categorized into West, Central, and East regions to enable analysis of spatial and hierarchical generalization.

The number of tree records and genera in the dataset, per city and per region. The holdout city (which is never seen during training in any capacity) for each region is in bold.

The Auto Arborist Dataset
To curate Auto Arborist, we started from existing tree censuses which are provided by many cities online. For each tree census considered, we verified that the data contained GPS locations and genus/species labels, and was available for public use. We then parsed these data into a common format, fixing common data entry errors (such as flipped latitude/longitude) and mapping ground-truth genus names (and their common misspellings or alternate names) to a unified taxonomy. We have chosen to focus on genus prediction (instead of species-level prediction) as our primary task to avoid taxonomic complexity arising from hybrid and subspecies and the fact that there is more universal consensus on genus names than species names.

Next, using the provided geolocation for each tree, we queried an RGB aerial image centered on the tree and all street-level images taken within 2-10 meters around it. Finally, we filtered these images to (1) maximize our chances that the tree of interest is visible from each image and (2) preserve user privacy. This latter concern involved a number of steps including the removal of images that included people as determined by semantic segmentation and manual blurring, among others.

Selected Street View imagery from the Auto Arborist dataset. Green boxes represent tree detections (using a model trained on Open Images) and blue dots represent projected GPS location of the labeled tree.

One of the most important challenges for urban forest monitoring is to do well in cities that were not part of the training set. Vision models must contend with distribution shifts, where the training distribution differs from the test distribution from a new city. Genus distributions vary geographically (e.g., there are more Douglas fir in western Canada than in California) and can also vary based on city size (LA is much larger than Santa Monica and contains many more genera). Another challenge is the long-tailed, fine-grained nature of tree genera, which can be difficult to disambiguate even for human experts, with many genera being quite rare.

The long-tailed distribution across Auto Arborist categories. Most examples come from a few frequent categories, and many categories have far fewer examples. We characterize each genus as frequent, common, or rare based on the number of training examples. Note that the test data is split spatially from the training data within each city, so not all rare genera are seen in the test set.

Finally, there are a number of ways in which tree images can have noise. For one, there is temporal variation in deciduous trees (for example, when aerial imagery includes leaves, but street-level images are bare). Moreover, public arboreal censuses are not always up-to-date. Thus, sometimes trees have died (and are no longer visible) in the time since the tree census was taken. In addition, aerial data quality can be poor (missing or obscured, e.g., by clouds).

Our curation process sought to minimize these issues by (1) only keeping images with sufficient tree pixels, as determined by a semantic segmentation model, (2) only keeping reasonably recent images, and (3) only keeping images where the tree position was sufficiently close to the street level camera. We considered also optimizing for trees seen in spring and summer, but decided seasonal variation could be a useful cue — we thus also released the date of each image to enable the community to explore the effects of seasonal variability.

Benchmark and Evaluation
To evaluate the dataset, we designed a benchmark to measure domain generalization and performance in the long tail of the distribution. We generated training and test splits at three levels. First, we split within each city (based on latitude or longitude) to see how well a city generalizes to itself. Second, we aggregate city-level training sets into three regions, West, Central, and East, holding out one city from each region. Finally, we merge the training sets across the three regions. For each of these splits, we report both accuracy and class-averaged recall for frequent, common and rare species on the corresponding held-out test sets.

Using these metrics, we establish a performance baseline using standard modern convolutional models (ResNet). Our results demonstrate the benefits of a large-scale, geospatially distributed dataset such as Auto Arborist. First, we see that more training data helps — training on the entire dataset is better than training on a region, which is better than training on a single city.

The performance on each city’s test set when training on itself, on the region, and on the full training set.

Second, training on similar cities helps (and thus, having more coverage of cities helps). For example, if focusing on Seattle, then it is better to train on trees in Vancouver than Pittsburgh.

Cross-set performance, looking at the pairwise combination of train and test sets for each city. Note the block-diagonal structure, which highlights regional structure in the dataset.

Third, more data modalities and views help. The best performing models combine inputs from multiple Street View angles and overhead views. There remains much room for improvement, however, and this is where we believe the larger community of researchers can help.

Get Involved
By releasing the Auto Arborist Dataset, we step closer to the goal of affordable urban forest monitoring, enabling the computer vision community to tackle urban forest monitoring at scale for the first time. In the future, we hope to expand coverage to more North American cities (particularly in the South of the US and Mexico) and even worldwide. Further, we are excited to push the dataset to the more fine-grained species level and investigate more nuanced monitoring, including monitoring tree health and growth over time, and studying the effects of environmental factors on urban forests.

For more details, see our CVPR 2022 paper. This dataset is part of Google’s broader efforts to empower cities with data about urban forests, through the Environmental Insights Explorer Tree Canopy Lab and is available on our GitHub repo. If you represent a city that is interested in being included in the dataset please email auto-arborist+managers@googlegroups.com.

Acknowledgements
We would like to thank our co-authors Guanhang Wu, Trevor Edwards, Filip Pavetic, Bo Majewski, Shreyasee Mukherjee, Stanley Chan, John Morgan, Vivek Rathod, and Chris Bauer. We also thank Ruth Alcantara, Tanya Birch, and Dan Morris from Google AI for Nature and Society, John Quintero, Stafford Marquardt, Xiaoqi Yin, Puneet Lall, and Matt Manolides from Google Geo, Karan Gill, Tom Duerig, Abhijit Kundu, David Ross, Vighnesh Birodkar from Google Research (Perception team), and Pietro Perona for their support. This work was supported in part by the Resnick Sustainability Institute and was undertaken while Sara Beery was a Student Researcher at Google.

Read More

Read More

Posted by Shaina Mehta and Kristen Borg, Program Managers

This week marks the beginning of the premier annual Computer Vision and Pattern Recognition conference (CVPR 2022), held both in-person in New Orleans, LA and virtually. As a leader in computer vision research and a Platinum Sponsor, Google will have a strong presence across CVPR 2022 with over 80 papers being presented at the main conference and active involvement in a number of conference workshops and tutorials.

If you are attending CVPR this year, please stop by our booth and chat with our researchers who are actively exploring the latest machine learning techniques for application to various areas of machine perception. Our researchers will also be available to talk about and demo several recent efforts, including on-device ML applications with MediaPipe, the Auto Arborist Dataset for urban forest monitoring, and much more.

You can also learn more about our research being presented at CVPR 2022 in the list below (Google affiliations in bold).

Organizing Committee

Tutorials Chairs
Include: Boqing Gong

Website Chairs
Include: AJ Piergiovanni

Area Chairs
Include: Alireza Fathi, Cordelia Schmid, Deqing Sun, Jonathan Barron, Michael Ryoo, Supasorn Suwajanakorn, Susanna Ricco

Diversity, Equity, and Inclusion Chairs
Include: Noah Snavely

Panel Discussion: Embodied Computer Vision
Panelists include: Michael Ryoo

Publications

Learning to Prompt for Continual Learning (see blog post)
Zifeng Wang^*, Zizhao Zhang, Chen-Yu Lee, Han Zhang, Ruoxi Sun, Xiaoqi Ren, Guolong Su, Vincent Perot, Jennifer Dy, Tomas Pfister

GCR: Gradient Coreset Based Replay Buffer Selection for Continual Learning
Rishabh Tiwari, Krishnateja Killamsetty, Rishabh Iyer, Pradeep Shenoy

Zero-Shot Text-Guided Object Generation with Dream Fields
Ajay Jain, Ben Mildenhall, Jonathan T. Barron, Pieter Abbeel, Ben Poole

Towards End-to-End Unified Scene Text Detection and Layout Analysis
Shangbang Long, Siyang Qin, Dmitry Panteleev, Alessandro Bissacco, Yasuhisa Fujii, Michalis Raptis

FLOAT: Factorized Learning of Object Attributes for Improved Multi-object Multi-part Scene Parsing
Rishubh Singh, Pranav Gupta, Pradeep Shenoy, Ravikiran Sarvadevabhatla

LOLNerf: Learn from One Look
Daniel Rebain, Mark Matthews, Kwang Moo Yi, Dmitry Lagun, Andrea Tagliasacchi

Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothing
Thiemo Alldieck, Mihai Zanfir, Cristian Sminchisescu

Learning Local Displacements for Point Cloud Completion
Yida Wang, David Joseph Tan, Nassir Navab, Federico Tombari

Density-Preserving Deep Point Cloud Compression
Yun He, Xinlin Ren, Danhang Tang, Yinda Zhang, Xiangyang Xue, Yanwei Fu

CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation
Qihang Yu^*, Huiyu Wang, Dahun Kim, Siyuan Qiao, Maxwell Collins, Yukun Zhu, Hartwig Adam, Alan Yuille, Liang-Chieh Chen

Deformable Sprites for Unsupervised Video Decomposition
Vickie Ye, Zhengqi Li, Richard Tucker, Angjoo Kanazawa, Noah Snavely

Learning with Neighbor Consistency for Noisy Labels
Ahmet Iscen, Jack Valmadre, Anurag Arnab, Cordelia Schmid

Multiview Transformers for Video Recognition
Shen Yan, Xuehan Xiong, Anurag Arnab, Zhichao Lu, Mi Zhang, Chen Sun, Cordelia Schmid

Kubric: A Scalable Dataset Generator
Klaus Greff, Francois Belletti, Lucas Beyer, Carl Doersch, Yilun Du, Daniel Duckworth, David J. Fleet, Dan Gnanapragasam, Florian Golemo, Charles Herrmann, Thomas Kipf, Abhijit Kundu, Dmitry Lagun, Issam Laradji, Hsueh-Ti (Derek) Liu, Henning Meyer, Yishu Miao, Derek Nowrouzezahrai, Cengiz Oztireli, Etienne Pot, Noha Radwan^*, Daniel Rebain, Sara Sabour, Mehdi S. M. Sajjadi, Matan Sela, Vincent Sitzmann, Austin Stone, Deqing Sun, Suhani Vora, Ziyu Wang, Tianhao Wu, Kwang Moo Yi, Fangcheng Zhong, Andrea Tagliasacchi

3D Moments from Near-Duplicate Photos
Qianqian Wang, Zhengqi Li, David Salesin, Noah Snavely, Brian Curless, Janne Kontkanen

Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields
Jonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan, Peter Hedman

RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs
Michael Niemeyer^*, Jonathan T. Barron, Ben Mildenhall, Mehdi S. M. Sajjadi, Andreas Geiger, Noha Radwan^*

Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields
Dor Verbin, Peter Hedman, Ben Mildenhall, Todd Zickler, Jonathan T. Barron, Pratul P. Srinivasan

IRON: Inverse Rendering by Optimizing Neural SDFs and Materials from Photometric Images
Kai Zhang, Fujun Luan, Zhengqi Li, Noah Snavely

MAXIM: Multi-Axis MLP for Image Processing
Zhengzhong Tu^*, Hossein Talebi, Han Zhang, Feng Yang, Peyman Milanfar, Alan Bovik, Yinxiao Li

Restormer: Efficient Transformer for High-Resolution Image Restoration
Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang

Burst Image Restoration and Enhancement
Akshay Dudhane, Syed Waqas Zamir, Salman Khan, Fahad Shahbaz Khan, Ming-Hsuan Yang

Neural RGB-D Surface Reconstruction
Dejan Azinović, Ricardo Martin-Brualla, Dan B Goldman, Matthias Nießner, Justus Thies

Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations
Mehdi S. M. Sajjadi, Henning Meyer, Etienne Pot, Urs Bergmann, Klaus Greff, Noha Radwan^*, Suhani Vora, Mario Lučić, Daniel Duckworth, Alexey Dosovitskiy^*, Jakob Uszkoreit^*, Thomas Funkhouser, Andrea Tagliasacchi^*

ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimation
Yongzhi Su, Mahdi Saleh, Torben Fetzer, Jason Rambach, Nassir Navab, Benjamin Busam, Didier Stricker, Federico Tombari

MetaPose: Fast 3D Pose from Multiple Views without 3D Supervision
Ben Usman, Andrea Tagliasacchi, Kate Saenko, Avneesh Sud

GPV-Pose: Category-Level Object Pose Estimation via Geometry-Guided Point-wise Voting
Yan Di, Ruida Zhang, Zhiqiang Lou, Fabian Manhardt, Xiangyang Ji, Nassir Navab, Federico Tombari

Rethinking Deep Face Restoration
Yang Zhao^*, Yu-Chuan Su, Chun-Te Chu, Yandong Li, Marius Renn, Yukun Zhu, Changyou Chen, Xuhui Jia

Transferability Metrics for Selecting Source Model Ensembles
Andrea Agostinelli, Jasper Uijlings, Thomas Mensink, Vittorio Ferrari

Robust Fine-Tuning of Zero-Shot Models
Mitchell Wortsman, Gabriel Ilharco, Jong Wook Kim, Mike Li, Simon Kornblith, Rebecca Roelofs, Raphael Gontijo Lopes, Hannaneh Hajishirzi, Ali Farhadi, Hongseok Namkoong, Ludwig Schmidt

Block-NeRF: Scalable Large Scene Neural View Synthesis
Matthew Tancik, Vincent Casser, Xinchen Yan, Sabeek Pradhan, Ben Mildenhall, Pratul P. Srinivasan, Jonathan T. Barron, Henrik Kretzschmar

Light Field Neural Rendering
Mohammad Suhail^*, Carlos Esteves, Leonid Sigal, Ameesh Makadia

Transferability Estimation Using Bhattacharyya Class Separability
Michal Pándy, Andrea Agostinelli, Jasper Uijlings, Vittorio Ferrari, Thomas Mensink

Matching Feature Sets for Few-Shot Image Classification
Arman Afrasiyabi, Hugo Larochelle, Jean-François Lalonde, Christian Gagné

Which Model to Transfer? Finding the Needle in the Growing Haystack
Cedric Renggli, André Susano Pinto, Luka Rimanic, Joan Puigcerver, Carlos Riquelme, Ce Zhang, Mario Lučić

Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakage
Zhuohang Li, Jiaxin Zhang, Luyang Liu, Jian Liu

Estimating Example Difficulty Using Variance of Gradients
Chirag Agarwal, Daniel D’souza, Sara Hooker

More Than Words: In-the-Wild Visually-Driven Prosody for Text-to-Speech (see blog post)
Michael Hassid, Michelle Tadmor Ramanovich, Brendan Shillingford, Miaosen Wang, Ye Jia, Tal Remez

Robust Outlier Detection by De-Biasing VAE Likelihoods
Kushal Chauhan, Barath Mohan U, Pradeep Shenoy, Manish Gupta, Devarajan Sridharan

Deep 3D-to-2D Watermarking: Embedding Messages in 3D Meshes and Extracting Them from 2D Renderings
Innfarn Yoo, Huiwen Chang, Xiyang Luo, Ondrej Stava, Ce Liu^*, Peyman Milanfar, Feng Yang

Knowledge Distillation: A Good Teacher Is Patient and Consistent
Lucas Beyer, Xiaohua Zhai, Amélie Royer^*, Larisa Markeeva^*, Rohan Anil, Alexander Kolesnikov

Urban Radiance Fields
Konstantinos Rematas, Andrew Liu, Pratul P. Srinivasan, Jonathan T. Barron, Andrea Tagliasacchi, Thomas Funkhouser, Vittorio Ferrari

Manifold Learning Benefits GANs
Yao Ni, Piotr Koniusz, Richard Hartley, Richard Nock

MaskGIT: Masked Generative Image Transformer
Huiwen Chang, Han Zhang, Lu Jiang, Ce Liu^*, William T. Freeman

InOut: Diverse Image Outpainting via GAN Inversion
Yen-Chi Cheng, Chieh Hubert Lin, Hsin-Ying Lee, Jian Ren, Sergey Tulyakov, Ming-Hsuan Yang

Scaling Vision Transformers (see blog post)
Xiaohua Zhai, Alexander Kolesnikov, Neil Houlsby, Lucas Beyer

Fine-Tuning Image Transformers Using Learnable Memory
Mark Sandler, Andrey Zhmoginov, Max Vladymyrov, Andrew Jackson

PokeBNN: A Binary Pursuit of Lightweight Accuracy
Yichi Zhang^*, Zhiru Zhang, Lukasz Lew

Bending Graphs: Hierarchical Shape Matching Using Gated Optimal Transport
Mahdi Saleh, Shun-Cheng Wu, Luca Cosmo, Nassir Navab, Benjamin Busam, Federico Tombari

Uncertainty-Aware Deep Multi-View Photometric Stereo
Berk Kaya, Suryansh Kumar, Carlos Oliveira, Vittorio Ferrari, Luc Van Gool

Depth-Supervised NeRF: Fewer Views and Faster Training for Free
Kangle Deng, Andrew Liu, Jun-Yan Zhu, Deva Ramanan

Dense Depth Priors for Neural Radiance Fields from Sparse Input Views
Barbara Roessle, Jonathan T. Barron, Ben Mildenhall, Pratul P. Srinivasan, Matthias Nießner

Trajectory Optimization for Physics-Based Reconstruction of 3D Human Pose from Monocular Video
Erik Gärtner, Mykhaylo Andriluka, Hongyi Xu, Cristian Sminchisescu

Differentiable Dynamics for Articulated 3D Human Motion Reconstruction
Erik Gärtner, Mykhaylo Andriluka, Erwin Coumans, Cristian Sminchisescu

Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation
Abhijit Kundu, Kyle Genova, Xiaoqi Yin, Alireza Fathi, Caroline Pantofaru, Leonidas J. Guibas, Andrea Tagliasacchi, Frank Dellaert, Thomas Funkhouser

Pyramid Adversarial Training Improves ViT Performance
Charles Herrmann, Kyle Sargent, Lu Jiang, Ramin Zabih, Huiwen Chang, Ce Liu^*, Dilip Krishnan, Deqing Sun

Proper Reuse of Image Classification Features Improves Object Detection
Cristina Vasconcelos, Vighnesh Birodkar, Vincent Dumoulin

SOMSI: Spherical Novel View Synthesis with Soft Occlusion Multi-Sphere Images
Tewodros Habtegebrial, Christiano Gava, Marcel Rogge, Didier Stricker, Varun Jampani

TubeFormer-DeepLab: Video Mask Transformer
Dahun Kim, Jun Xie, Huiyu Wang, Siyuan Qiao, Qihang Yu, Hong-Seok Kim, Hartwig Adam, In So Kweon, Liang-Chieh Chen

Contextualized Spatio-Temporal Contrastive Learning with Self-Supervision
Liangzhe Yuan, Rui Qian^*, Yin Cui, Boqing Gong, Florian Schroff, Ming-Hsuan Yang, Hartwig Adam, Ting Liu

When Does Contrastive Visual Representation Learning Work?
Elijah Cole, Xuan Yang, Kimberly Wilber, Oisin Mac Aodha, Serge Belongie

Less Is More: Generating Grounded Navigation Instructions from Landmarks
Su Wang, Ceslee Montgomery, Jordi Orbay, Vighnesh Birodkar, Aleksandra Faust, Izzeddin Gur, Natasha Jaques, Austin Waters, Jason Baldridge, Peter Anderson

Forecasting Characteristic 3D Poses of Human Actions
Christian Diller, Thomas Funkhouser, Angela Dai

BEHAVE: Dataset and Method for Tracking Human Object Interactions
Bharat Lal Bhatnagar, Xianghui Xie, Ilya A. Petrov, Cristian Sminchisescu, Christian Theobalt, Gerard Pons-Moll

Motion-from-Blur: 3D Shape and Motion Estimation of Motion-Blurred Objects in Videos
Denys Rozumnyi, Martin R. Oswald, Vittorio Ferrari, Marc Pollefeys

End-to-End Generative Pretraining for Multimodal Video Captioning (see blog post)
Paul Hongsuck Seo, Arsha Nagrani, Anurag Arnab, Cordelia Schmid

Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation
Jogendra Nath Kundu, Siddharth Seth, Pradyumna YM, Varun Jampani, Anirban Chakraborty, R. Venkatesh Babu

Learning ABCs: Approximate Bijective Correspondence for Isolating Factors of Variation with Weak Supervision
Kieran A. Murphy, Varun Jampani, Srikumar Ramalingam, Ameesh Makadia

HumanNeRF: Free-Viewpoint Rendering of Moving People from Monocular Video
Chung-Yi Weng, Brian Curless, Pratul P. Srinivasan, Jonathan T. Barron, Ira Kemelmacher-Shlizerman

Deblurring via Stochastic Refinement
Jay Whang^*, Mauricio Delbracio, Hossein Talebi, Chitwan Saharia, Alexandros G. Dimakis, Peyman Milanfar

NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images
Ben Mildenhall, Peter Hedman, Ricardo Martin-Brualla, Pratul P. Srinivasan, Jonathan T. Barron

CoNeRF: Controllable Neural Radiance Fields
Kacper Kania, Kwang Moo Yi, Marek Kowalski, Tomasz Trzciński, Andrea Tagliasacchi

A Conservative Approach for Unbiased Learning on Unknown Biases
Myeongho Jeon, Daekyung Kim, Woochul Lee, Myungjoo Kang, Joonseok Lee

DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection (see blog post)
Yingwei Li^*, Adams Wei Yu, Tianjian Meng, Ben Caine, Jiquan Ngiam, Daiyi Peng, Junyang Shen, Yifeng Lu, Denny Zhou, Quoc V. Le, Alan Yuille, Mingxing Tan

Video Frame Interpolation Transformer
Zhihao Shi, Xiangyu Xu, Xiaohong Liu, Jun Chen, Ming-Hsuan Yang

Global Matching with Overlapping Attention for Optical Flow Estimation
Shiyu Zhao, Long Zhao, Zhixing Zhang, Enyu Zhou, Dimitris Metaxas

LiT: Zero-Shot Transfer with Locked-image Text Tuning (see blog post)
Xiaohua Zhai, Xiao Wang, Basil Mustafa, Andreas Steiner, Daniel Keysers, Alexander Kolesnikov, Lucas Beyer

Are Multimodal Transformers Robust to Missing Modality?
Mengmeng Ma, Jian Ren, Long Zhao, Davide Testuggine, Xi Peng

3D-VField: Adversarial Augmentation of Point Clouds for Domain Generalization in 3D Object Detection
Alexander Lehner, Stefano Gasperini, Alvaro Marcos-Ramiro, Michael Schmidt, Mohammad-Ali Nikouei Mahani, Nassir Navab, Benjamin Busam, Federico Tombari

SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation
Tao Sun, Mattia Segu, Janis Postels, Yuxuan Wang, Luc Van Gool, Bernt Schiele, Federico Tombari, Fisher Yu

H4D: Human 4D Modeling by Learning Neural Compositional Representation
Boyan Jiang, Yinda Zhang, Xingkui Wei, Xiangyang Xue, Yanwei Fu

Gravitationally Lensed Black Hole Emission Tomography
Aviad Levis, Pratul P. Srinivasan, Andrew A. Chael, Ren Ng, Katherine L. Bouman

Deep Saliency Prior for Reducing Visual Distraction
Kfir Aberman, Junfeng He, Yossi Gandelsman, Inbar Mosseri, David E. Jacobs, Kai Kohlhoff, Yael Pritch, Michael Rubinstein

The Auto Arborist Dataset: A Large-Scale Benchmark for Multiview Urban Forest Monitoring Under Domain Shift
Sara Beery, Guanhang Wu, Trevor Edwards, Filip Pavetic, Bo Majewski, Shreyasee Mukherjee, Stanley Chan, John Morgan, Vivek Rathod, Jonathan Huang

Workshops

Ethical Considerations in Creative Applications of Computer Vision
Chairs and Advisors: Negar Rostamzadeh, Fernando Diaz, Emily Denton, Mark Diaz, Jason Baldridge

Dynamic Neural Networks Meet Computer Vision Organizers
Invited Speaker: Barret Zoph

Precognition: Seeing Through the Future
Organizer: Utsav Prabhu
Invited Speaker: Sella Nevo

Computer Vision in the Built Environment for the Design, Construction, and Operation of Buildings
Invited Speakers: Thomas Funkhouser, Federico Tombari

Neural Architecture Search: Lightweight NAS Challenge
Invited Speaker: Barret Zoph

Transformers in Vision
Organizer: Lucas Beyer
Invited Speakers and Panelists: Alexander Kolesnikov, Mathilde Caron, Arsha Nagrani, Lucas Beyer

Challenge on Learned Image Compression
Organizers: George Toderici, Johannes Balle, Eirikur Agustsson, Nick Johnston, Fabian Mentzer, Luca Versari
Invited Speaker: Debargha Mukherjee

Embodied AI
Organizers: Anthony Francis, Sören Pirk, Alex Ku, Fei Xia, Peter Anderson
Scientific Advisory Board Members: Alexander Toshev, Jie Tan
Invited Speaker: Carolina Parada

Sight and Sound
Organizers: Arsha Nagrani, William Freeman

New Trends in Image Restoration and Enhancement
Organizers: Ming-Hsuan Yang, Vivek Kwatra, George Toderici

EarthVision: Large Scale Computer Vision for Remote Sensing Imagery
Invited Speaker: John Quinn

LatinX in Computer Vision Research
Organizer: Ruben Villegas

Fine-Grained Visual Categorization
Organizer: Kimberly Wilber

The Art of Robustness: Devil and Angel in Adversarial Machine Learning
Organizer: Florian Tramèr
Invited Speaker: Nicholas Carlini

AI for Content Creation
Organizers: Deqing Sun, Huiwen Chang, Lu Jiang
Invited Speaker: Chitwan Saharia

LOng-form VidEo Understanding
Invited Speaker: Cordelia Schmid

Visual Perception and Learning in an Open World
Invited Speaker: Rahul Sukthankar

Media Forensics
Organizer : Christoph Bregler
Technical Committee Members: Shruti Agarwal, Scott McCloskey, Peng Zhou

Vision Datasets Understanding
Organizer: José Lezama

Embedded Vision
Invited Speaker: Matthias Grundmann

Federated Learning for Computer Vision
Invited Speaker: Zheng Xu

Large Scale Holistic Video Understanding
Organizer: David Ross
Invited Speaker: Anurag Arnab

Learning With Limited Labelled Data for Image and Video Understanding
Invited Speaker: Hugo Larochelle

Bridging the Gap Between Computational Photography and Visual Recognition
Invited Speaker: Xiaohua Zhai

Explainable Artificial Intelligence for Computer Vision
Invited Speaker: Been Kim

Robustness in Sequential Data
Organizers: Sayna Ebrahimi, Kevin Murphy
Invited Speakers: Sayna Ebrahimi, Balaji Lakshminarayanan

Sketch-Oriented Deep Learning
Organizer: David Ha
Invited Speaker: Jonas Jongejan

Multimodal Learning and Applications
Invited Speaker: Cordelia Schmid

Computational Cameras and Displays
Organizer: Tali Dekel
Invited Speaker: Peyman Millanfar

Artificial Social Intelligence
Invited Speaker: Natasha Jaques

VizWiz Grand Challenge: Algorithms to Assist People Who Are Blind
Invited Speaker and Panelist: Andrew Howard

Image Matching: Local Features & Beyond
Organizer: Eduard Trulls

Multi-Agent Behavior: Representation, Modeling, Measurement, and Applications
Organizer: Ting Liu

Efficient Deep Learning for Computer Vision
Organizers: Pete Warden, Andrew Howard, Grace Chu, Jaeyoun Kim

Gaze Estimation and Prediction in the Wild
Organizer: Thabo Beeler

Tutorials

Denoising Diffusion-Based Generative Modeling: Foundations and Applications
Invited Speaker: Ruiqi Gao

Algorithmic Fairness: Why It’s Hard and Why It’s Interesting
Invited Speaker: Sanmi Koyejo

Beyond Convolutional Neural Networks
Invited Speakers: Neil Houlsby, Alexander Kolesnikov, Xiaohua Zhai

Joint Ego4D and Egocentric Perception, Interaction & Computing
Invited Speaker: Vittorio Ferrari

Deep AUC Maximization
Invited Speakers: Tianbao Yang

Vision-Based Robot Learning
Organizers: Michael S. Ryoo, Andy Zeng, Pete Florence

Graph Machine Learning for Visual Computing
Organizers: Federico Tombari
Invited Speakers: Federico Tombari, Fabian Manhardt

Read More

Posted by Laura Downs and Anthony Francis, Software Engineers, Robotics at Google

Many recent advances in computer vision and robotics rely on deep learning, but training deep learning models requires a wide variety of data to generalize to new scenarios. Historically, deep learning for computer vision has relied on datasets with millions of items that were gathered by web scraping, examples of which include ImageNet, Open Images, YouTube-8M, and COCO. However, the process of creating these datasets can be labor-intensive, and can still exhibit labeling errors that can distort the perception of progress. Furthermore, this strategy does not readily generalize to arbitrary three-dimensional shapes or real-world robotic data.

Real-world robotic data collection is very useful, but difficult to scale and challenging to label.

Simulating robots and environments using tools such as Gazebo, MuJoCo, and Unity can mitigate many of the inherent limitations in these datasets. However, simulation is only an approximation of reality — handcrafted models built from polygons and primitives often correspond poorly to real objects. Even if a scene is built directly from a 3D scan of a real environment, the movable objects in that scan will act like fixed background scenery and will not respond the way real-world objects would. Due to these challenges, there are few large libraries with high-quality models of 3D objects that can be incorporated into physical and visual simulations to provide the variety needed for deep learning.

In “Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items”, presented at ICRA 2022, we describe our efforts to address this need by creating the Scanned Objects dataset, a curated collection of over 1000 3D-scanned common household items. The Scanned Objects dataset is usable in tools that read Simulation Description Format (SDF) models, including the Gazebo and PyBullet robotics simulators. Scanned Objects is hosted on Open Robotics, an open-source hosting environment for models compatible with the Gazebo simulator.

History
Robotics researchers within Google began scanning objects in 2011, creating high-fidelity 3D models of common household objects to help robots recognize and grasp things in their environments. However, it became apparent that 3D models have many uses beyond object recognition and robotic grasping, including scene construction for physical simulations and 3D object visualization for end-user applications. Therefore, this Scanned Objects project was expanded to bring 3D experiences to Google at scale, collecting a large number of 3D scans of household objects through a process that is more efficient and cost effective than traditional commercial-grade product photography.

Scanned Objects was an end-to-end effort, involving innovations at nearly every stage of the process, including curation of objects at scale for 3D scanning, the development of novel 3D scanning hardware, efficient 3D scanning software, fast 3D rendering software for quality assurance, and specialized frontends for web and mobile viewers. We also executed human-computer interaction studies to create effective experiences for interacting with 3D objects.

Objects that were acquired for scanning.

These object models proved useful in 3D visualizations for Everyday Robots, which used the models to bridge the sim-to-real gap for training, work later published as RetinaGAN and RL-CycleGAN. Building on these earlier 3D scanning efforts, in 2019 we began preparing an external version of the Scanned Objects dataset and transforming the previous set of 3D images into graspable 3D models.

Object Scanning
To create high-quality models, we built a scanning rig to capture images of an object from multiple directions under controlled and carefully calibrated conditions. The system consists of two machine vision cameras for shape detection, a DSLR camera for high-quality HDR color frame extraction, and a computer-controlled projector for pattern recognition. The scanning rig uses a structured light technique that infers a 3D shape from camera images with patterns of light that are projected onto an object.

The scanning rig used to capture 3D models.

Simulation Model Conversion
The early internal scanned models used protocol buffer metadata, high-resolution visuals, and formats that were not suitable for simulation. For some objects, physical properties, such as mass, were captured by weighing the objects at scanning time, but surface properties, such as friction or deformation, were not represented.

So, following data collection, we built an automated pipeline to solve these issues and enable the use of scanned models in simulation systems. The automated pipeline filters out invalid or duplicate objects, automatically assigns object names using text descriptions of the objects, and eliminates object mesh scans that do not meet simulation requirements. Next, the pipeline estimates simulation properties (e.g., mass and moment of inertia) from shape and volume, constructs collision volumes, and downscales the model to a usable size. Finally, the pipeline converts each model to SDF format, creates thumbnail images, and packages the model for use in simulation systems.

The pipeline filters models that are not suitable for simulation, generates collision volumes, computes physical properties, downsamples meshes, generates thumbnails, and packages them all for use in simulation systems.

A collection of Scanned Object models rendered in Blender.

The output of this pipeline is a simulation model in an appropriate format with a name, mass, friction, inertia, and collision information, along with searchable metadata in a public interface compatible with our open-source hosting on Open Robotics’ Gazebo.

The output objects are represented as SDF models that refer to Wavefront OBJ meshes averaging 1.4 Mb per model. Textures for these models are in PNG format and average 11.2 Mb. Together, these provide high resolution shape and texture.

Impact
The Scanned Objects dataset contains 1030 scanned objects and their associated metadata, totaling 13 Gb, licensed under the CC-BY 4.0 License. Because these models are scanned rather than modeled by hand, they realistically reflect real object properties, not idealized recreations, reducing the difficulty of transferring learning from simulation to the real world.

Input views (left) and reconstructed shape and texture from two novel views on the right (figure from Differentiable Stereopsis).

Visualized action scoring predictions over three real-world 3D scans from the Replica dataset and Scanned Objects (figure from Where2Act).

The Scanned Objects dataset has already been used in over 25 papers across as many projects, spanning computer vision, computer graphics, robot manipulation, robot navigation, and 3D shape processing. Most projects used the dataset to provide synthetic training data for learning algorithms. For example, the Scanned Objects dataset was used in Kubric, an open-sourced generator of scalable datasets for use in over a dozen vision tasks, and in LAX-RAY, a system for searching shelves with lateral access X-rays to automate the mechanical search for occluded objects on shelves.

Unsupervised 3D keypoints on real-world data (figure from KeypointDeformer).

We hope that the Scanned Objects dataset will be used by more robotics and simulation researchers in the future, and that the example set by this dataset will inspire other owners of 3D model repositories to make them available for researchers everywhere. If you would like to try it yourself, head to Gazebo and start browsing!

Acknowledgments
The authors thank the Scanned Objects team, including Peter Anderson-Sprecher, J.J. Blumenkranz, James Bruce, Ken Conley, Katie Dektar, Charles DuHadway, Anthony Francis, Chaitanya Gharpure, Topraj Gurung, Kristy Headley, Ryan Hickman, John Isidoro, Sumit Jain, Brandon Kinman, Greg Kline, Mach Kobayashi, Nate Koenig, Kai Kohlhoff, James Kuffner, Thor Lewis, Mike Licitra, Lexi Martin, Julian (Mac) Mason, Rus Maxham, Pascal Muetschard, Kannan Pashupathy, Barbara Petit, Arshan Poursohi, Jared Russell, Matt Seegmiller, John Sheu, Joe Taylor, Josh Weaver, and Tommy McHugh.

Special thanks go to Krista Reyman for organizing this project, helping write the paper, and editing this blogpost, James Bruce for the scanning pipeline design and Pascal Muetschard for maintaining the database of object models.

Read More

Posted by Basil Mustafa, Research Software Engineer and Carlos Riquelme, Research Scientist, Google Research, Brain team

Sparse models stand out among the most promising approaches for the future of deep learning. Instead of every part of a model processing every input (“dense” modeling), sparse models employing conditional computation learn to route individual inputs to different “experts” in a potentially huge network. This has many benefits. First, model size can increase while keeping computational cost constant — an effective and environmentally friendlier way to scale models, which is often key to high performance. Sparsity also naturally compartmentalizes neural networks. Dense models that learn many different tasks simultaneously (multitask) or sequentially (continual learning) often suffer negative interference, where too much task variety means it is better to just train one model per task, or catastrophic forgetting, where the model becomes worse at earlier tasks as new ones are added. Sparse models help avoid both these phenomena — by not applying the whole model to all inputs, “experts” in the model can specialize on different tasks or data types while still taking advantage of shared parts of the model.

Research on sparsity has long been pursued at Google Research. Pathways summarizes the research vision of building one single large model that diligently handles thousands of tasks and numerous data modalities. So far there has been considerable progress in sparse unimodal models for language (Switch, Task-MoE, GLaM) and computer vision (Vision MoE). Today, we take another important step towards the Pathways vision by studying large sparse models that simultaneously handle images and text with modality-agnostic routing. A relevant approach is multimodal contrastive learning, which requires a solid understanding of both images and text in order to align pictures with their correct text description. The strongest models that tackle this task to date rely on independent networks for each modality (a “two-tower” approach).

In “Multimodal Contrastive Learning with LIMoE: the Language Image Mixture of Experts”, we present the first large-scale multimodal architecture using a sparse mixture of experts. It simultaneously processes both images and text, but uses sparsely activated experts that naturally specialize. On zero-shot image classification, LIMoE outperforms both comparable dense multimodal models and two-tower approaches. The largest LIMoE achieves 84.1% zero-shot ImageNet accuracy, comparable to more expensive state-of-the-art models. Sparsity enables LIMoE to scale up gracefully and learn to handle very different inputs, addressing the tension between being a jack-of-all-trades generalist and a master-of-one specialist.

The LIMoE architecture contains many “experts” and routers decide which tokens (parts of an image or sentence) go to which experts. After being processed by expert layers (gray) and shared dense layers (brown), a final output layer computes a single vector representation for either an image or a text.

Sparse Mixture of Expert Models
Transformers represent data as a sequence of vectors (or tokens). Though originally developed for text, they can be applied to most things that are representable as a sequence of tokens, e.g., images, videos, and audio. Recent large-scale MoE models add expert layers to the Transformer architecture (e.g., gShard and ST-MoE in natural language processing, and Vision MoE for vision tasks).

A standard Transformer consists of many “blocks”, each containing various different layers. One of these layers is a feed-forward network (FFN). For LIMoE and the works cited above, this single FFN is replaced by an expert layer that contains many parallel FFNs, each of which is an expert. Given a sequence of tokens to process, a simple router learns to predict which experts should handle which tokens. Only a small number of experts are activated per token, meaning although the model capacity is significantly increased by virtue of having so many experts, the actual computational cost is controlled by using them sparsely. If only one expert is activated, the model’s cost is roughly equivalent to the standard Transformer model.

LIMoE does precisely that, activating one expert per example, thereby matching the computational cost of the dense baselines. What’s different is that the LIMoE router might see tokens of either image or text data.

A unique failure mode of MoE models occurs when they try to send all tokens to the same expert. Typically this is addressed with auxiliary losses, extra training objectives that encourage balanced expert usage. We found that dealing with multiple modalities interacted with sparsity to cause new failure modes that existing auxiliary losses could not address. To overcome this, we developed new auxiliary losses (more details in the paper) and used routing prioritization (BPR) during training, two innovations that resulted in stable and high performance multimodal models.

The new auxiliary losses (LIMoE aux) and routing prioritization (BPR) stabilized and improved overall performance (left) and increased the success rate of routing behavior (middle and right). A low success rate means the router does not use all the experts available and drops many tokens due to individual expert capacity being reached, which usually indicates the sparse model is not learning well. The combination introduced for LIMoE ensures high routing success rates for both images and text and consequently leads to significantly better performance.

Contrastive Learning with LIMoE
In multimodal contrastive learning, models are trained on paired image-text data (e.g., a photo and its caption). Typically, an image model extracts a representation of images, and a different text model extracts a representation of text. The contrastive learning objective encourages the image and text representations to be close for the same image-text pair and far away for content from different pairs. Such models with aligned representations can be adapted to new tasks without extra training data (“zero-shot”), e.g., an image will be classified as a dog if its representation is closer to the representation of the word “dog” than the word “cat”. This idea scales to thousands of classes and is referred to as zero-shot image classification.

CLIP and ALIGN (both two-tower models) scaled this process to achieve 76.2% and 76.4% zero-shot classification accuracy on the popular ImageNet dataset. We study one-tower models which compute both image and text representations. We find this reduces performance for dense models, likely due to negative interference or insufficient capacity. However, a compute-matched LIMoE not only improves over the one-tower dense model, but also outperforms two-tower dense models. We trained a series of models in a comparable training regimen to CLIP. Our dense L/16 model achieves 73.5% zero-shot accuracy, whereas LIMoE-L/16 gets to 78.6%, even outperforming CLIP’s more expensive, two-tower L/14 model (76.2%). As shown below, LIMoE’s use of sparsity provides a remarkable performance boost over dense models with equivalent cost.

For a given compute cost (x-axis), LIMoE models (circles, solid line) are significantly better than their dense baselines (triangles, dashed line). The architecture indicates the size of the underlying transformer, increasing from left (S/32) to right (L/16). Following standard convention, S (small), B (base), and L (large) refer to model scale. The number refers to the patch size, where smaller patches imply a larger architecture.

LiT and BASIC pushed zero-shot accuracy for dense two-tower models to 84.5% and 85.6% respectively. In addition to scaling, these approaches made use of specialized pre-training methods, repurposing image models that were already of exceptionally high quality. LIMoE-H/14 does not benefit from any pre-training or modality-specific components, but still achieved a comparable 84.1% zero-shot accuracy training from scratch. The scale of these models is also interesting to compare: LiT and BASIC are 2.1B and 3B parameter models. LIMoE-H/14 has 5.6B parameters in total, but via sparsity it only applies 675M parameters per token making it significantly more lightweight.

Understanding LIMoE’s Behavior
LIMoE was motivated by the intuition that sparse conditional computation enables a generalist multimodal model to still develop the specialization needed to excel at understanding each modality. We analyzed LIMoE’s expert layers and uncovered a few interesting phenomena.

First, we see the emergence of modality-specialized experts. In our training setup there are many more image tokens than text tokens, so all experts tend to process at least some images, but some experts process either mostly images, mostly text, or both.

Distributions for an eight expert LIMoE; percentages indicate the amount of image tokens processed by the expert. There are one or two experts clearly specialized on text (shown by the mostly blue experts), usually two to four image specialists (mostly red), and the remainder are somewhere in the middle.

There are also some clear qualitative patterns among the image experts — e.g., in most LIMoE models, there is an expert that processes all image patches that contain text. In the example below, one expert processes fauna and greenery, and another processes human hands.

LIMoE chooses an expert for each token. Here we show which image tokens go to which experts on one of the layers of LIMoE-H/14. Despite not being trained to do so, we observe the emergence of semantic experts that specialize in specific topics such as plants or wheels.

Moving Forward
Multimodal models that handle many tasks are a promising route forward, and there are two key ingredients for success: scale, and the ability to avoid interference between distinct tasks and modalities while taking advantage of synergies. Sparse conditional computation is an excellent way of doing both. It enables performant and efficient generalist models that also have the capacity and flexibility for the specialization necessary to excel at individual tasks, as demonstrated by LIMoE’s solid performance with less compute.

Acknowledgements
We thank our co-authors on this work: Joan Puigcerver, Rodolphe Jenatton and Neil Houlsby. We also thank Andreas Steiner, Xiao Wang and Xiaohua Zhai, who led early explorations into dense single-tower models for contrastive multimodal learning, and also were instrumental in providing data access. We enjoyed useful discussions with André Susano Pinto, Maxim Neumann, Barret Zoph, Liam Fedus, Wei Han and Josip Djolonga. Finally, we would also like to thank and acknowledge Tom Small for the awesome animated figure used in this post.

Read More

Read More

Posted by Paul Hongsuck Seo and Arsha Nagrani, Research Scientists, Google Research, Perception Team

Multimodal video captioning systems utilize both the video frames and speech to generate natural language descriptions (captions) of videos. Such systems are stepping stones towards the longstanding goal of building multimodal conversational systems that effortlessly communicate with users while perceiving environments through multimodal input streams.

Unlike video understanding tasks (e.g., video classification and retrieval) where the key challenge lies in processing and understanding multimodal input videos, the task of multimodal video captioning includes the additional challenge of generating grounded captions. The most widely adopted approach for this task is to train an encoder-decoder network jointly using manually annotated data. However, due to a lack of large-scale, manually annotated data, the task of annotating grounded captions for videos is labor intensive and, in many cases, impractical. Previous research such as VideoBERT and CoMVT pre-train their models on unlabelled videos by leveraging automatic speech recognition (ASR). However, such models often cannot generate natural language sentences because they lack a decoder, and thus only the video encoder is transferred to the downstream tasks.

In “End-to-End Generative Pre-training for Multimodal Video Captioning”, published at CVPR 2022, we introduce a novel pre-training framework for multimodal video captioning. This framework, which we call multimodal video generative pre-training or MV-GPT, jointly trains a multimodal video encoder and a sentence decoder from unlabelled videos by leveraging a future utterance as the target text and formulating a novel bi-directional generation task. We demonstrate that MV-GPT effectively transfers to multimodal video captioning, achieving state-of-the-art results on various benchmarks. Additionally, the multimodal video encoder is competitive for multiple video understanding tasks, such as VideoQA, text-video retrieval, and action recognition.

Future Utterance as an Additional Text Signal
Typically, each training video clip for multimodal video captioning is associated with two different texts: (1) a speech transcript that is aligned with the clip as a part of the multimodal input stream, and (2) a target caption, which is often manually annotated. The encoder learns to fuse information from the transcript with visual contents, and the target caption is used to train the decoder for generation. However, in the case of unlabelled videos, each video clip comes only with a transcript from ASR, without a manually annotated target caption. Moreover, we cannot use the same text (the ASR transcript) for the encoder input and decoder target, since the generation of the target would then be trivial.

MV-GPT circumvents this challenge by leveraging a future utterance as an additional text signal and enabling joint pre-training of the encoder and decoder. However, training a model to generate future utterances that are often not grounded in the input content is not ideal. So we apply a novel bi-directional generation loss to reinforce the connection to the input.

Bi-directional Generation Loss
The issue of non-grounded text generation is mitigated by formulating a bi-directional generation loss that includes forward and backward generation. Forward generation produces future utterances given visual frames and their corresponding transcripts and allows the model to learn to fuse the visual content with its corresponding transcript. Backward generation takes the visual frames and future utterances to train the model to generate a transcript that contains more grounded text of the video clip. Bi-directional generation loss in MV-GPT allows the encoder and the decoder to be trained to handle visually grounded texts.

Bi-directional generation in MV-GPT. A model is trained with two generation losses. In forward generation, the model generates a future utterance (blue boxes) given the frames and the present utterance (red boxes), whereas the present is generated from the future utterance in backward generation. Two special beginning-of-sentence tokens ([BOS-F] and [BOS-B]) initiate forward and backward generation for the decoder.

Results on Multimodal Video Captioning
We compare MV-GPT to existing pre-training losses using the same model architecture, on YouCook2 with standard evaluation metrics (Bleu-4, Cider, Meteor and Rouge-L). While all pre-training techniques improve captioning performances, it is critical to pre-train the decoder jointly to improve model performance. We demonstrate that MV-GPT outperforms the previous state-of-the-art joint pre-training method by over 3.5% with relative gains across all four metrics.

We transfer a model pre-trained by MV-GPT to four different captioning benchmarks: YouCook2, MSR-VTT, ViTT and ActivityNet-Captions. Our model achieves state-of-the-art performance on all four benchmarks by significant margins. For instance on the Meteor metric, MV-GPT shows over 12% relative improvements in all four benchmarks.

Results on Non-generative Video Understanding Tasks
Although MV-GPT is designed to train a generative model for multimodal video captioning, we also find that our pre-training technique learns a powerful multimodal video encoder that can be applied to multiple video understanding tasks, including VideoQA, text-video retrieval and action classification. When compared to the best comparable baseline models, the model transferred from MV-GPT shows superior performance in five video understanding benchmarks on their primary metrics — i.e., top-1 accuracy for VideoQA and action classification benchmarks, and recall at 1 for the retrieval benchmark.

Summary
We introduce MV-GPT, a new generative pre-training framework for multimodal video captioning. Our bi-directional generative objective jointly pre-trains a multimodal encoder and a caption decoder by using utterances sampled at different times in unlabelled videos. Our pre-trained model achieves state-of-the-art results on multiple video captioning benchmarks and other video understanding tasks, namely VideoQA, video retrieval and action classification.

Acknowledgements
This research was conducted by Paul Hongsuck Seo, Arsha Nagrani, Anurag Arnab and Cordelia Schmid.

Read More

Posted by Pasin Manurangsi and Chiyuan Zhang, Research Scientists, Google Research

Over the last several years, there has been an increased focus on developing differential privacy (DP) machine learning (ML) algorithms. DP has been the basis of several practical deployments in industry — and has even been employed by the U.S. Census — because it enables the understanding of system and algorithm privacy guarantees. The underlying assumption of DP is that changing a single user’s contribution to an algorithm should not significantly change its output distribution.

In the standard supervised learning setting, a model is trained to make a prediction of the label for each input given a training set of example pairs {[input₁,label₁], …, [input_n, label_n]}. In the case of deep learning, previous work introduced a DP training framework, DP-SGD, that was integrated into TensorFlow and PyTorch. DP-SGD protects the privacy of each example pair [input, label] by adding noise to the stochastic gradient descent (SGD) training algorithm. Yet despite extensive efforts, in most cases, the accuracy of models trained with DP-SGD remains significantly lower than that of non-private models.

DP algorithms include a privacy budget, ε, which quantifies the worst-case privacy loss for each user. Specifically, ε reflects how much the probability of any particular output of a DP algorithm can change if one replaces any example of the training set with an arbitrarily different one. So, a smaller ε corresponds to better privacy, as the algorithm is more indifferent to changes of a single example. However, since smaller ε tends to hurt model utility more, it is not uncommon to consider ε up to 8 in deep learning applications. Notably, for the widely used multiclass image classification dataset, CIFAR-10, the highest reported accuracy (without pre-training) for DP models with ε = 3 is 69.3%, a result that relies on handcrafted visual features. In contrast, non-private scenarios (ε = ∞) with learned features have shown to achieve >95% accuracy while using modern neural network architectures. This performance gap remains a roadblock for many real-world applications to adopt DP. Moreover, despite recent advances, DP-SGD often comes with increased computation and memory overhead due to slower convergence and the need to compute the norm of the per-example gradient.

In “Deep Learning with Label Differential Privacy”, presented at NeurIPS 2021, we consider a more relaxed, but important, special case called label differential privacy (LabelDP), where we assume the inputs (input₁, …, input_n) are public, and only the privacy of the training labels (label₁, …, label_n) needs to be protected. With this relaxed guarantee, we can design novel algorithms that utilize a prior understanding of the labels to improve the model utility. We demonstrate that LabelDP achieves 20% higher accuracy than DP-SGD on the CIFAR-10 dataset. Our results across multiple tasks confirm that LabelDP could significantly narrow the performance gap between private models and their non-private counterparts, mitigating the challenges in real world applications. We also present a multi-stage algorithm for training deep neural networks with LabelDP. Finally, we are excited to release the code for this multi-stage training algorithm.

LabelDP
The notion of LabelDP has been studied in the Probably Approximately Correct (PAC) learning setting, and captures several practical scenarios. Examples include: (i) computational advertising, where impressions are known to the advertiser and thus considered non-sensitive, but conversions reveal user interest and are thus private; (ii) recommendation systems, where the choices are known to a streaming service provider, but the user ratings are considered sensitive; and (iii) user surveys and analytics, where demographic information (e.g., age, gender) is non-sensitive, but income is sensitive.

We make several key observations in this scenario. (i) When only the labels need to be protected, much simpler algorithms can be applied for data preprocessing to achieve LabelDP without any modifications to the existing deep learning training pipeline. For example, the classic Randomized Response (RR) algorithm, designed to eliminate evasive answer biases in survey aggregation, achieves LabelDP by simply flipping the label to a random one with a probability that depends on ε. (ii) Conditioned on the (public) input, we can compute a prior probability distribution, which provides a prior belief of the likelihood of the class labels for the given input. With a novel variant of RR, RR-with-prior, we can incorporate prior information to reduce the label noise while maintaining the same privacy guarantee as classical RR.

The figure below illustrates how RR-with-prior works. Assume a model is built to classify an input image into 10 categories. Consider a training example with the label “airplane”. To guarantee LabelDP, classical RR returns a random label sampled according to a given distribution (see the top-right panel of the figure below). The smaller the targeted privacy budget ε is, the larger the probability of sampling an incorrect label has to be. Now assume we have a prior probability showing that the given input is “likely an object that flies” (lower left panel). With the prior, RR-with-prior will discard all labels with small prior and only sample from the remaining labels. By dropping these unlikely labels, the probability of returning the correct label is significantly increased, while maintaining the same privacy budget ε (lower right panel).

Randomized response: If no prior information is given (top-left), all classes are sampled with equal probability. The probability of sampling the true class (P[airplane] ≈ 0.5) is higher if the privacy budget is higher (top-right). RR-with-prior: Assuming a prior distribution (bottom-left), unlikely classes are “suppressed” from the sampling distribution (bottom-right). So the probability of sampling the true class (P[airplane] ≈ 0.9) is increased under the same privacy budget.

A Multi-stage Training Algorithm
Based on the RR-with-prior observations, we present a multi-stage algorithm for training deep neural networks with LabelDP. First, the training set is randomly partitioned into multiple subsets. An initial model is then trained on the first subset using classical RR. Finally, the algorithm divides the data into multiple parts, and at each stage, a single part is used to train the model. The labels are produced using RR-with-prior, and the priors are based on the prediction of the model trained so far.

An illustration of the multi-stage training algorithm. The training set is partitioned into t disjoint subsets. An initial model is trained on the first subset using classical RR. Then the trained model is used to provide prior predictions in the RR-with-prior step and in the training of the later stages.

Results
We benchmark the multi-stage training algorithm’s empirical performance on multiple datasets, domains, and architectures. On the CIFAR-10 multi-class classification task for the same privacy budget ε, the multi-stage training algorithm (blue in the figure below) guaranteeing LabelDP achieves 20% higher accuracy than DP-SGD. We emphasize that LabelDP protects only the labels while DP-SGD protects both the inputs and labels, so this is not a strictly fair comparison. Nonetheless, this result demonstrates that for specific application scenarios where only the labels need to be protected, LabelDP could lead to significant improvements in the model utility while narrowing the performance gap between private models and public baselines.

Comparison of the model utility (test accuracy) of different algorithms under different privacy budgets.

In some domains, prior knowledge is naturally available or can be built using publicly available data only. For example, many machine learning systems have historical models which could be evaluated on new data to provide label priors. In domains where unsupervised or self-supervised learning algorithms work well, priors could also be built from models pre-trained on unlabeled (therefore public with respect to LabelDP) data. Specifically, we demonstrate two self-supervised learning algorithms in our CIFAR-10 evaluation (orange and green traces in the figure above). We use self-supervised learning models to compute representations for the training examples and run k-means clustering on the representations. Then, we spend a small amount of privacy budget (ε ≤ 0.05) to query a histogram of the label distribution of each cluster and use that as the label prior for the points in each cluster. This prior significantly boosts the model utility in the low privacy budget regime (ε < 1).

Similar observations hold across multiple datasets such as MNIST, Fashion-MNIST and non-vision domains, such as the MovieLens-1M movie rating task. Please see our paper for the full report on the empirical results.

The empirical results suggest that protecting the privacy of the labels can be significantly easier than protecting the privacy of both the inputs and labels. This can also be mathematically proven under specific settings. In particular, we can show that for convex stochastic optimization, the sample complexity of algorithms privatizing the labels is much smaller than that of algorithms privatizing both labels and inputs. In other words, to achieve the same level of model utility under the same privacy budget, LabelDP requires fewer training examples.

Conclusion
We demonstrated that both empirical and theoretical results suggest that LabelDP is a promising relaxation of the full DP guarantee. In applications where the privacy of the inputs does not need to be protected, LabelDP could reduce the performance gap between a private model and the non-private baseline. For future work, we plan to design better LabelDP algorithms for other tasks beyond multi-class classification. We hope that the release of the multi-stage training algorithm code provides researchers with a useful resource for DP research.

Acknowledgements
This work was carried out in collaboration with Badih Ghazi, Noah Golowich, and Ravi Kumar. We also thank Sami Torbey for valuable feedback on our work.

Read More