Andrew Jaegle

Olivier J. Hénaff, Skanda Koppula, Evan Shelhamer et al. · deepmind

The promise of self-supervised learning (SSL) is to leverage large amounts of unlabeled data to solve complex tasks. While there has been excellent progress with simple, image-level learning, recent methods have shown the advantage of including knowledge of image structure. However, by introducing hand-crafted image segmentations to define regions of interest, or specialized augmentation strategies, these methods sacrifice the simplicity and generality that makes SSL so powerful. Instead, we propose a self-supervised learning paradigm that discovers this image structure by itself. Our method, Odin, couples object discovery and representation networks to discover meaningful image segmentations without any supervision. The resulting learning paradigm is simpler, less brittle, and more general, and achieves state-of-the-art transfer learning results for object detection and instance segmentation on COCO, and semantic segmentation on PASCAL and Cityscapes, while strongly surpassing supervised pre-training for video segmentation on DAVIS.

Drew A. Hudson, Daniel Zoran, Mateusz Malinowski et al. · deepmind, stanford

We introduce SODA, a self-supervised diffusion model, designed for representation learning. The model incorporates an image encoder, which distills a source view into a compact representation, that, in turn, guides the generation of related novel views. We show that by imposing a tight bottleneck between the encoder and a denoising decoder, and leveraging novel view synthesis as a self-supervised objective, we can turn diffusion models into strong representation learners, capable of capturing visual semantics in an unsupervised manner. To the best of our knowledge, SODA is the first diffusion model to succeed at ImageNet linear-probe classification, and, at the same time, it accomplishes reconstruction, editing and synthesis tasks across a wide range of datasets. Further investigation reveals the disentangled nature of its emergent latent space, that serves as an effective interface to control and manipulate the model's produced images. All in all, we aim to shed light on the exciting and promising potential of diffusion models, not only for image generation, but also for learning rich and robust representations.

Jannik Kossen, Cătălina Cangea, Eszter Vértes et al. · cambridge

We introduce a challenging decision-making task that we call active acquisition for multimodal temporal data (A2MT). In many real-world scenarios, input features are not readily available at test time and must instead be acquired at significant cost. With A2MT, we aim to learn agents that actively select which modalities of an input to acquire, trading off acquisition cost and predictive performance. A2MT extends a previous task called active feature acquisition to temporal decision making about high-dimensional inputs. We propose a method based on the Perceiver IO architecture to address A2MT in practice. Our agents are able to solve a novel synthetic scenario requiring practically relevant cross-modal reasoning skills. On two large-scale, real-world datasets, Kinetics-700 and AudioSet, our agents successfully learn cost-reactive acquisition behavior. However, an ablation reveals they are unable to learn adaptive acquisition strategies, emphasizing the difficulty of the task even for state-of-the-art models. Applications of A2MT may be impactful in domains like medicine, robotics, or finance, where modalities differ in acquisition cost and informativeness.

Charlie Nash, João Carreira, Jacob Walker et al.

We present a general-purpose framework for image modelling and vision tasks based on probabilistic frame prediction. Our approach unifies a broad range of tasks, from image segmentation, to novel view synthesis and video interpolation. We pair this framework with an architecture we term Transframer, which uses U-Net and Transformer components to condition on annotated context frames, and outputs sequences of sparse, compressed image features. Transframer is the state-of-the-art on a variety of video generation benchmarks, is competitive with the strongest models on few-shot view synthesis, and can generate coherent 30 second videos from a single image without any explicit geometric information. A single generalist Transframer simultaneously produces promising results on 8 tasks, including semantic segmentation, image classification and optical flow prediction with no task-specific architectural components, demonstrating that multi-task computer vision can be tackled using probabilistic image models. Our approach can in principle be applied to a wide range of applications that require learning the conditional structure of annotated image-formatted data.

Skanda Koppula, Yazhe Li, Evan Shelhamer et al.

Self-supervised methods have achieved remarkable success in transfer learning, often achieving the same or better accuracy than supervised pre-training. Most prior work has done so by increasing pre-training computation by adding complex data augmentation, multiple views, or lengthy training schedules. In this work, we investigate a related, but orthogonal question: given a fixed FLOP budget, what are the best datasets, models, and (self-)supervised training methods for obtaining high accuracy on representative visual tasks? Given the availability of large datasets, this setting is often more relevant for both academic and industry labs alike. We examine five large-scale datasets (JFT-300M, ALIGN, ImageNet-1K, ImageNet-21K, and COCO) and six pre-training methods (CLIP, DINO, SimCLR, BYOL, Masked Autoencoding, and supervised). In a like-for-like fashion, we characterize their FLOP and CO$_2$ footprints, relative to their accuracy when transferred to a canonical image segmentation task. Our analysis reveals strong disparities in the computational efficiency of pre-training methods and their dependence on dataset quality. In particular, our results call into question the commonly-held assumption that self-supervised methods inherently scale to large, uncurated data. We therefore advocate for (1) paying closer attention to dataset curation and (2) reporting of accuracies in context of the total computational cost.

David L Barack, Andrew Jaegle

We argue that intelligence, construed as the disposition to perform tasks successfully, is a property of systems composed of agents and their contexts. This is the thesis of extended intelligence. We argue that the performance of an agent will generally not be preserved if its context is allowed to vary. Hence, this disposition is not possessed by an agent alone, but is rather possessed by the system consisting of an agent and its context, which we dub an agent-in-context. An agent's context may include an environment, other agents, cultural artifacts (like language, technology), or all of these, as is typically the case for humans and artificial intelligence systems, as well as many non-human animals. In virtue of the thesis of extended intelligence, we contend that intelligence is context-bound, task-particular and incommensurable among agents. Our thesis carries strong implications for how intelligence is analyzed in the context of both psychology and artificial intelligence.

Aditi Sundararaman, Amogh Adishesha, Andrew Jaegle et al.

From professional filmmaking to user-generated content, creators and consumers have long recognized that the power of video depends on the harmonious integration of what we hear (the video's audio track) with what we see (the video's image sequence). Current approaches to video generation either ignore sound to focus on general-purpose but silent image sequence generation or address both visual and audio elements but focus on restricted application domains such as re-dubbing. We introduce Mirage, an audio-to-video foundation model that excels at generating realistic, expressive output imagery from scratch given an audio input. When integrated with existing methods for speech synthesis (text-to-speech, or TTS), Mirage results in compelling multimodal video. When trained on audio-video footage of people talking (A-roll) and conditioned on audio containing speech, Mirage generates video of people delivering a believable interpretation of the performance implicit in input audio. Our central technical contribution is a unified method for training self-attention-based audio-to-video generation models, either from scratch or given existing weights. This methodology allows Mirage to retain generality as an approach to audio-to-video generation while producing outputs of superior subjective quality to methods that incorporate audio-specific architectures or loss components specific to people, speech, or details of how images or audio are captured. We encourage readers to watch and listen to the results of Mirage for themselves (see paper and comments for links).

Joao Carreira, Skanda Koppula, Daniel Zoran et al.

General perception systems such as Perceivers can process arbitrary modalities in any combination and are able to handle up to a few hundred thousand inputs. They achieve this generality by using exclusively global attention operations. This however hinders them from scaling up to the inputs sizes required to process raw high-resolution images or video. In this paper, we show that some degree of locality can be introduced back into these models, greatly improving their efficiency while preserving their generality. To scale them further, we introduce a self-supervised approach that enables learning dense low-dimensional positional embeddings for very large signals. We call the resulting model a Hierarchical Perceiver (HiP). In sum our contributions are: 1) scaling Perceiver-type models to raw high-resolution images and audio+video, 2) showing the feasibility of learning 1M+ positional embeddings from scratch using masked auto-encoding, 3) demonstrating competitive performance on raw data from ImageNet, AudioSet, PASCAL VOC, ModelNet40 and Kinetics datasets with the same exact, unchanged model and without specialized preprocessing or any tokenization.

Curtis Hawthorne, Andrew Jaegle, Cătălina Cangea et al.

Real-world data is high-dimensional: a book, image, or musical performance can easily contain hundreds of thousands of elements even after compression. However, the most commonly used autoregressive models, Transformers, are prohibitively expensive to scale to the number of inputs and layers needed to capture this long-range structure. We develop Perceiver AR, an autoregressive, modality-agnostic architecture which uses cross-attention to map long-range inputs to a small number of latents while also maintaining end-to-end causal masking. Perceiver AR can directly attend to over a hundred thousand tokens, enabling practical long-context density estimation without the need for hand-crafted sparsity patterns or memory mechanisms. When trained on images or music, Perceiver AR generates outputs with clear long-term coherence and structure. Our architecture also obtains state-of-the-art likelihood on long-sequence benchmarks, including 64 x 64 ImageNet images and PG-19 books.

Luyu Wang, Pauline Luc, Yan Wu et al.

The ability to learn universal audio representations that can solve diverse speech, music, and environment tasks can spur many applications that require general sound content understanding. In this work, we introduce a holistic audio representation evaluation suite (HARES) spanning 12 downstream tasks across audio domains and provide a thorough empirical study of recent sound representation learning systems on that benchmark. We discover that previous sound event classification or speech models do not generalize outside of their domains. We observe that more robust audio representations can be learned with the SimCLR objective; however, the model's transferability depends heavily on the model architecture. We find the Slowfast architecture is good at learning rich representations required by different domains, but its performance is affected by the normalization scheme. Based on these findings, we propose a novel normalizer-free Slowfast NFNet and achieve state-of-the-art performance across all domains.

Irina Higgins, Peter Wirnsberger, Andrew Jaegle et al.

A recently proposed class of models attempts to learn latent dynamics from high-dimensional observations, like images, using priors informed by Hamiltonian mechanics. While these models have important potential applications in areas like robotics or autonomous driving, there is currently no good way to evaluate their performance: existing methods primarily rely on image reconstruction quality, which does not always reflect the quality of the learnt latent dynamics. In this work, we empirically highlight the problems with the existing measures and develop a set of new measures, including a binary indicator of whether the underlying Hamiltonian dynamics have been faithfully captured, which we call Symplecticity Metric or SyMetric. Our measures take advantage of the known properties of Hamiltonian dynamics and are more discriminative of the model's ability to capture the underlying dynamics than reconstruction error. Using SyMetric, we identify a set of architectural choices that significantly improve the performance of a previously proposed model for inferring latent dynamics from pixels, the Hamiltonian Generative Network (HGN). Unlike the original HGN, the new HGN++ is able to discover an interpretable phase space with physically meaningful latents on some datasets. Furthermore, it is stable for significantly longer rollouts on a diverse range of 13 datasets, producing rollouts of essentially infinite length both forward and backwards in time with no degradation in quality on a subset of the datasets.

Aleksandar Botev, Andrew Jaegle, Peter Wirnsberger et al.

Learning dynamics is at the heart of many important applications of machine learning (ML), such as robotics and autonomous driving. In these settings, ML algorithms typically need to reason about a physical system using high dimensional observations, such as images, without access to the underlying state. Recently, several methods have proposed to integrate priors from classical mechanics into ML models to address the challenge of physical reasoning from images. In this work, we take a sober look at the current capabilities of these models. To this end, we introduce a suite consisting of 17 datasets with visual observations based on physical systems exhibiting a wide range of dynamics. We conduct a thorough and detailed comparison of the major classes of physically inspired methods alongside several strong baselines. While models that incorporate physical priors can often learn latent spaces with desirable properties, our results demonstrate that these methods fail to significantly improve upon standard techniques. Nonetheless, we find that the use of continuous and time-reversible dynamics benefits models of all classes.

Andrew Jaegle, Sebastian Borgeaud, Jean-Baptiste Alayrac et al.

A central goal of machine learning is the development of systems that can solve many problems in as many data domains as possible. Current architectures, however, cannot be applied beyond a small set of stereotyped settings, as they bake in domain & task assumptions or scale poorly to large inputs or outputs. In this work, we propose Perceiver IO, a general-purpose architecture that handles data from arbitrary settings while scaling linearly with the size of inputs and outputs. Our model augments the Perceiver with a flexible querying mechanism that enables outputs of various sizes and semantics, doing away with the need for task-specific architecture engineering. The same architecture achieves strong results on tasks spanning natural language and visual understanding, multi-task and multi-modal reasoning, and StarCraft II. As highlights, Perceiver IO outperforms a Transformer-based BERT baseline on the GLUE language benchmark despite removing input tokenization and achieves state-of-the-art performance on Sintel optical flow estimation with no explicit mechanisms for multiscale correspondence.

Andrew Jaegle, Yury Sulsky, Arun Ahuja et al.

Imitation learning enables agents to reuse and adapt the hard-won expertise of others, offering a solution to several key challenges in learning behavior. Although it is easy to observe behavior in the real-world, the underlying actions may not be accessible. We present a new method for imitation solely from observations that achieves comparable performance to experts on challenging continuous control tasks while also exhibiting robustness in the presence of observations unrelated to the task. Our method, which we call FORM (for "Future Observation Reward Model") is derived from an inverse RL objective and imitates using a model of expert behavior learned by generative modelling of the expert's observations, without needing ground truth actions. We show that FORM performs comparably to a strong baseline IRL method (GAIL) on the DeepMind Control Suite benchmark, while outperforming GAIL in the presence of task-irrelevant features.

Andrew Jaegle, Felix Gimeno, Andrew Brock et al.

Biological systems perceive the world by simultaneously processing high-dimensional inputs from modalities as diverse as vision, audition, touch, proprioception, etc. The perception models used in deep learning on the other hand are designed for individual modalities, often relying on domain-specific assumptions such as the local grid structures exploited by virtually all existing vision models. These priors introduce helpful inductive biases, but also lock models to individual modalities. In this paper we introduce the Perceiver - a model that builds upon Transformers and hence makes few architectural assumptions about the relationship between its inputs, but that also scales to hundreds of thousands of inputs, like ConvNets. The model leverages an asymmetric attention mechanism to iteratively distill inputs into a tight latent bottleneck, allowing it to scale to handle very large inputs. We show that this architecture is competitive with or outperforms strong, specialized models on classification tasks across various modalities: images, point clouds, audio, video, and video+audio. The Perceiver obtains performance comparable to ResNet-50 and ViT on ImageNet without 2D convolutions by directly attending to 50,000 pixels. It is also competitive in all modalities in AudioSet.

Karl Tuyls, Shayegan Omidshafiei, Paul Muller et al.

The rapid progress in artificial intelligence (AI) and machine learning has opened unprecedented analytics possibilities in various team and individual sports, including baseball, basketball, and tennis. More recently, AI techniques have been applied to football, due to a huge increase in data collection by professional teams, increased computational power, and advances in machine learning, with the goal of better addressing new scientific challenges involved in the analysis of both individual players' and coordinated teams' behaviors. The research challenges associated with predictive and prescriptive football analytics require new developments and progress at the intersection of statistical learning, game theory, and computer vision. In this paper, we provide an overarching perspective highlighting how the combination of these fields, in particular, forms a unique microcosm for AI research, while offering mutual benefits for professional teams, spectators, and broadcasters in the years to come. We illustrate that this duality makes football analytics a game changer of tremendous value, in terms of not only changing the game of football itself, but also in terms of what this domain can mean for the field of AI. We review the state-of-the-art and exemplify the types of analysis enabled by combining the aforementioned fields, including illustrative examples of counterfactual analysis using predictive models, and the combination of game-theoretic analysis of penalty kicks with statistical learning of player attributes. We conclude by highlighting envisioned downstream impacts, including possibilities for extensions to other sports (real and virtual).

Peter Karkus, Mehdi Mirza, Arthur Guez et al.

Intelligent robots need to achieve abstract objectives using concrete, spatiotemporally complex sensory information and motor control. Tabula rasa deep reinforcement learning (RL) has tackled demanding tasks in terms of either visual, abstract, or physical reasoning, but solving these jointly remains a formidable challenge. One recent, unsolved benchmark task that integrates these challenges is Mujoban, where a robot needs to arrange 3D warehouses generated from 2D Sokoban puzzles. We explore whether integrated tasks like Mujoban can be solved by composing RL modules together in a sense-plan-act hierarchy, where modules have well-defined roles similarly to classic robot architectures. Unlike classic architectures that are typically model-based, we use only model-free modules trained with RL or supervised learning. We find that our modular RL approach dramatically outperforms the state-of-the-art monolithic RL agent on Mujoban. Further, learned modules can be reused when, e.g., using a different robot platform to solve the same task. Together our results give strong evidence for the importance of research into modular RL designs. Project website: https://sites.google.com/view/modular-rl/

Mehdi Mirza, Andrew Jaegle, Jonathan J. Hunt et al.

Recent work in deep reinforcement learning (RL) has produced algorithms capable of mastering challenging games such as Go, chess, or shogi. In these works the RL agent directly observes the natural state of the game and controls that state directly with its actions. However, when humans play such games, they do not just reason about the moves but also interact with their physical environment. They understand the state of the game by looking at the physical board in front of them and modify it by manipulating pieces using touch and fine-grained motor control. Mastering complicated physical systems with abstract goals is a central challenge for artificial intelligence, but it remains out of reach for existing RL algorithms. To encourage progress towards this goal we introduce a set of physically embedded planning problems and make them publicly available. We embed challenging symbolic tasks (Sokoban, tic-tac-toe, and Go) in a physics engine to produce a set of tasks that require perception, reasoning, and motor control over long time horizons. Although existing RL algorithms can tackle the symbolic versions of these tasks, we find that they struggle to master even the simplest of their physically embedded counterparts. As a first step towards characterizing the space of solution to these tasks, we introduce a strong baseline that uses a pre-trained expert game player to provide hints in the abstract space to an RL agent's policy while training it on the full sensorimotor control task. The resulting agent solves many of the tasks, underlining the need for methods that bridge the gap between abstract planning and embodied control. See illustrating video at https://youtu.be/RwHiHlym_1k.

Peter Toth, Danilo Jimenez Rezende, Andrew Jaegle et al.

The Hamiltonian formalism plays a central role in classical and quantum physics. Hamiltonians are the main tool for modelling the continuous time evolution of systems with conserved quantities, and they come equipped with many useful properties, like time reversibility and smooth interpolation in time. These properties are important for many machine learning problems - from sequence prediction to reinforcement learning and density modelling - but are not typically provided out of the box by standard tools such as recurrent neural networks. In this paper, we introduce the Hamiltonian Generative Network (HGN), the first approach capable of consistently learning Hamiltonian dynamics from high-dimensional observations (such as images) without restrictive domain assumptions. Once trained, we can use HGN to sample new trajectories, perform rollouts both forward and backward in time and even speed up or slow down the learned dynamics. We demonstrate how a simple modification of the network architecture turns HGN into a powerful normalising flow model, called Neural Hamiltonian Flow (NHF), that uses Hamiltonian dynamics to model expressive densities. We hope that our work serves as a first practical demonstration of the value that the Hamiltonian formalism can bring to deep learning.

David Barack, Andrew Jaegle

In a recent article, Brette argues that coding as a concept is inappropriate for explanations of neurocognitive phenomena. Here, we argue that Brette's conceptual analysis mischaracterizes the structure of causal claims in coding and other forms of analysis-by-decomposition. We argue that analyses of this form are permissible, conceptually coherent, and offer essential tools for building and developing models of neurocognitive systems like the brain.

Karl Pertsch, Oleh Rybkin, Jingyun Yang et al.

Temporal observations such as videos contain essential information about the dynamics of the underlying scene, but they are often interleaved with inessential, predictable details. One way of dealing with this problem is by focusing on the most informative moments in a sequence. We propose a model that learns to discover these important events and the times when they occur and uses them to represent the full sequence. We do so using a hierarchical Keyframe-Inpainter (KeyIn) model that first generates a video's keyframes and then inpaints the rest by generating the frames at the intervening times. We propose a fully differentiable formulation to efficiently learn this procedure. We show that KeyIn finds informative keyframes in several datasets with different dynamics and visual properties. KeyIn outperforms other recent hierarchical predictive models for planning. For more details, please see the project website at \url{https://sites.google.com/view/keyin}.

Oleh Rybkin, Karl Pertsch, Konstantinos G. Derpanis et al.

Intelligent agents can learn to represent the action spaces of other agents simply by observing them act. Such representations help agents quickly learn to predict the effects of their own actions on the environment and to plan complex action sequences. In this work, we address the problem of learning an agent's action space purely from visual observation. We use stochastic video prediction to learn a latent variable that captures the scene's dynamics while being minimally sensitive to the scene's static content. We introduce a loss term that encourages the network to capture the composability of visual sequences and show that it leads to representations that disentangle the structure of actions. We call the full model with composable action representations Composable Learned Action Space Predictor (CLASP). We show the applicability of our method to synthetic settings and its potential to capture action spaces in complex, realistic visual settings. When used in a semi-supervised setting, our learned representations perform comparably to existing fully supervised methods on tasks such as action-conditioned video prediction and planning in the learned action space, while requiring orders of magnitude fewer action labels. Project website: https://daniilidis-group.github.io/learned_action_spaces

Andrew Jaegle, Oleh Rybkin, Konstantinos G. Derpanis et al.

An intelligent observer looks at the world and sees not only what is, but what is moving and what can be moved. In other words, the observer sees how the present state of the world can transform in the future. We propose a model that predicts future images by learning to represent the present state and its transformation given only a sequence of images. To do so, we introduce an architecture with a latent state composed of two components designed to capture (i) the present image state and (ii) the transformation between present and future states, respectively. We couple this latent state with a recurrent neural network (RNN) core that predicts future frames by transforming past states into future states by applying the accumulated state transformation with a learned operator. We describe how this model can be integrated into an encoder-decoder convolutional neural network (CNN) architecture that uses weighted residual connections to integrate representations of the past with representations of the future. Qualitatively, our approach generates image sequences that are stable and capture realistic motion over multiple predicted frames, without requiring adversarial training. Quantitatively, our method achieves prediction results comparable to state-of-the-art results on standard image prediction benchmarks (Moving MNIST, KTH, and UCF101).

Andrew Jaegle, Stephen Phillips, Daphne Ippolito et al.

Motion is an important signal for agents in dynamic environments, but learning to represent motion from unlabeled video is a difficult and underconstrained problem. We propose a model of motion based on elementary group properties of transformations and use it to train a representation of image motion. While most methods of estimating motion are based on pixel-level constraints, we use these group properties to constrain the abstract representation of motion itself. We demonstrate that a deep neural network trained using this method captures motion in both synthetic 2D sequences and real-world sequences of vehicle motion, without requiring any labels. Networks trained to respect these constraints implicitly identify the image characteristic of motion in different sequence types. In the context of vehicle motion, this method extracts information useful for localization, tracking, and odometry. Our results demonstrate that this representation is useful for learning motion in the general setting where explicit labels are difficult to obtain.

Andrew Jaegle, Stephen Phillips, Kostas Daniilidis

We propose robust methods for estimating camera egomotion in noisy, real-world monocular image sequences in the general case of unknown observer rotation and translation with two views and a small baseline. This is a difficult problem because of the nonconvex cost function of the perspective camera motion equation and because of non-Gaussian noise arising from noisy optical flow estimates and scene non-rigidity. To address this problem, we introduce the expected residual likelihood method (ERL), which estimates confidence weights for noisy optical flow data using likelihood distributions of the residuals of the flow field under a range of counterfactual model parameters. We show that ERL is effective at identifying outliers and recovering appropriate confidence weights in many settings. We compare ERL to a novel formulation of the perspective camera motion equation using a lifted kernel, a recently proposed optimization framework for joint parameter and confidence weight estimation with good empirical properties. We incorporate these strategies into a motion estimation pipeline that avoids falling into local minima. We find that ERL outperforms the lifted kernel method and baseline monocular egomotion estimation strategies on the challenging KITTI dataset, while adding almost no runtime cost over baseline egomotion methods.