We introduce SODA, a self-supervised diffusion model, designed for representation learning. The model incorpo-rates 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 ob-jective, we can turn diffusion models into strong represen-tation 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 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 represen-tations. See our website at soda-diffusion.github.io.

We propose a novel multimodal video benchmark - the Perception Test - to evaluate the perception and reasoning skills of pre-trained multimodal models (e.g. Flamingo, BEiT-3, or GPT-4). Compared to existing benchmarks that focus on computational tasks (e.g. classification, detection or tracking), the Perception Test focuses on skills (Memory, Abstraction, Physics, Semantics) and types of reasoning (descriptive, explanatory, predictive, counterfactual) across video, audio, and text modalities, to provide a comprehensive and efficient evaluation tool. The benchmark probes pre-trained models for their transfer capabilities, in a zero-shot / few-shot or limited finetuning regime. For these purposes, the Perception Test introduces 11.6k real-world videos, 23s average length, designed to show perceptually interesting situations, filmed by around 100 participants worldwide. The videos are densely annotated with six types of labels (multiple-choice and grounded video question-answers, object and point tracks, temporal action and sound segments), enabling both language and non-language evaluations. The fine-tuning and validation splits of the benchmark are publicly available (CC-BY license), in addition to a challenge server with a held-out test split. Human baseline results compared to state-of-the-art video QA models show a significant gap in performance (91.4% vs 45.8%), suggesting that there is significant room for improvement in multimodal video understanding.Dataset, baselines code, and challenge server are available at https://github.com/deepmind/perception_test

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 64x64 ImageNet images and PG-19 books.

In many multi-agent settings, participants can form teams to achieve collective outcomes that may far surpass their individual capabilities. Measuring the relative contributions of agents and allocating them shares of the reward that promote long-lasting cooperation are difficult tasks. Cooperative game theory offers solution concepts identifying distribution schemes, such as the Shapley value, that fairly reflect the contribution of individuals to the performance of the team or the Core, which reduces the incentive of agents to abandon their team. Applications of such methods include identifying influential features and sharing the costs of joint ventures or team formation. Unfortunately, using these solutions requires tackling a computational barrier as they are hard to compute, even in restricted settings. In this work, we show how cooperative game-theoretic solutions can be distilled into a learned model by training neural networks to propose fair and stable payoff allocations. We show that our approach creates models that can generalize to games far from the training distribution and can predict solutions for more players than observed during training. An important application of our framework is Explainable AI: our approach can be used to speed-up Shapley value computations on many instances.

How can neural networks be trained on large-volume temporal data efficiently? To compute the gradients required to update parameters, backpropagation blocks computations until the forward and backward passes are completed. For temporal signals, this introduces high latency and hinders real-time learning. It also creates a coupling between consecutive layers, which limits model parallelism and increases memory consumption. In this paper, we build upon Sideways, which avoids blocking by propagating approximate gradients forward in time, and we propose mechanisms for temporal integration of information based on different variants of skip connections. We also show how to decouple computation and delegate individual neural modules to different devices, allowing distributed and parallel training. The proposed Skip-Sideways achieves low latency training, model parallelism, and, importantly, is capable of extracting temporal features, leading to more stable training and improved performance on real-world action recognition video datasets such as HMDB51, UCF101, and the large-scale Kinetics-600. Finally, we also show that models trained with Skip-Sideways generate better future frames than Sideways models, and hence they can better utilize motion cues.

Most successful self-supervised learning methods are trained to align the representations of two independent views from the data. State-of-the-art methods in video are inspired by image techniques, where these two views are similarly extracted by cropping and augmenting the resulting crop. However, these methods miss a crucial element in the video domain: time. We introduce BraVe, a self-supervised learning framework for video. In BraVe, one of the views has access to a narrow temporal window of the video while the other view has a broad access to the video content. Our models learn to generalise from the narrow view to the general content of the video. Furthermore, BraVe processes the views with different backbones, enabling the use of alternative augmentations or modalities into the broad view such as optical flow, randomly convolved RGB frames, audio or their combinations. We demonstrate that BraVe achieves state-of-the-art results in self-supervised representation learning on standard video and audio classification benchmarks including UCF101, HMDB51, Kinetics, ESC-50 and AudioSet.

Navigating and understanding the real world remains a key challenge in machine learning and inspires a great variety of research in areas such as language grounding, planning, navigation and computer vision. We propose an instruction-following task that requires all of the above, and which combines the practicality of simulated environments with the challenges of ambiguous, noisy real world data. StreetNav is built on top of Google Street View and provides visually accurate environments representing real places. Agents are given driving instructions which they must learn to interpret in order to successfully navigate in this environment. Since humans equipped with driving instructions can readily navigate in previously unseen cities, we set a high bar and test our trained agents for similar cognitive capabilities. Although deep reinforcement learning (RL) methods are frequently evaluated only on data that closely follow the training distribution, our dataset extends to multiple cities and has a clean train/test separation. This allows for thorough testing of generalisation ability. This paper presents the StreetNav environment and tasks, models that establish strong baselines, and extensive analysis of the task and the trained agents.

We propose Sideways, an approximate backpropagation scheme for training video models. In standard backpropagation, the gradients and activations at every computation step through the model are temporally synchronized. The forward activations need to be stored until the backward pass is executed, preventing inter-layer (depth) parallelization. However, can we leverage smooth, redundant input streams such as videos to develop a more efficient training scheme? Here, we explore an alternative to backpropagation; we overwrite network activations whenever new ones, i.e., from new frames, become available. Such a more gradual accumulation of information from both passes breaks the precise correspondence between gradients and activations, leading to theoretically more noisy weight updates. Counter-intuitively, we show that Sideways training of deep convolutional video networks not only still converges, but can also potentially exhibit better generalization compared to standard synchronized backpropagation.

There are thousands of actively spoken languages on Earth, but a single visual world. Grounding in this visual world has the potential to bridge the gap between all these languages. Our goal is to use visual grounding to improve unsupervised word mapping between languages. The key idea is to establish a common visual representation between two languages by learning embeddings from unpaired instructional videos narrated in the native language. Given this shared embedding we demonstrate that (i) we can map words between the languages, particularly the 'visual' words; (ii) that the shared embedding provides a good initialization for existing unsupervised text-based word translation techniques, forming the basis for our proposed hybrid visual-text mapping algorithm, MUVE; and (iii) our approach achieves superior performance by addressing the shortcomings of text-based methods -- it is more robust, handles datasets with less commonality, and is applicable to low-resource languages. We apply these methods to translate words from English to French, Korean, and Japanese -- all without any parallel corpora and simply by watching many videos of people speaking while doing things.

Polynomial inequalities lie at the heart of many mathematical disciplines. In this paper, we consider the fundamental computational task of automatically searching for proofs of polynomial inequalities. We adopt the framework of semi-algebraic proof systems that manipulate polynomial inequalities via elementary inference rules that infer new inequalities from the premises. These proof systems are known to be very powerful, but searching for proofs remains a major difficulty. In this work, we introduce a machine learning based method to search for a dynamic proof within these proof systems. We propose a deep reinforcement learning framework that learns an embedding of the polynomials and guides the choice of inference rules, taking the inherent symmetries of the problem as an inductive bias. We compare our approach with powerful and widely-studied linear programming hierarchies based on static proof systems, and show that our method reduces the size of the linear program by several orders of magnitude while also improving performance. These results hence pave the way towards augmenting powerful and well-studied semi-algebraic proof systems with machine learning guiding strategies for enhancing the expressivity of such proof systems.

Boundary estimation in images and videos has been a very active topic of research, and organizing visual information into boundaries and segments is believed to be a corner stone of visual perception. While prior work has focused on estimating boundaries for observed frames, our work aims at predicting boundaries of future unobserved frames. This requires our model to learn about the fate of boundaries and corresponding motion patterns---including a notion of "intuitive physics." We experiment on natural video sequences along with synthetic sequences with deterministic physics-based and agent-based motions. While not being our primary goal, we also show that fusion of RGB and boundary prediction leads to improved RGB predictions.

Navigating through unstructured environments is a basic capability of intelligent creatures, and thus is of fundamental interest in the study and development of artificial intelligence. Long-range navigation is a complex cognitive task that relies on developing an internal representation of space, grounded by recognisable landmarks and robust visual processing, that can simultaneously support continuous self-localisation ("I am here") and a representation of the goal ("I am going there"). Building upon recent research that applies deep reinforcement learning to maze navigation problems, we present an end-to-end deep reinforcement learning approach that can be applied on a city scale. Recognising that successful navigation relies on integration of general policies with locale-specific knowledge, we propose a dual pathway architecture that allows locale-specific features to be encapsulated, while still enabling transfer to multiple cities. A key contribution of this paper is an interactive navigation environment that uses Google Street View for its photographic content and worldwide coverage. Our baselines demonstrate that deep reinforcement learning agents can learn to navigate in multiple cities and to traverse to target destinations that may be kilometres away. A video summarizing our research and showing the trained agent in diverse city environments as well as on the transfer task is available at: https://sites.google.com/view/learn-navigate-cities-nips18

Relational reasoning is a central component of generally intelligent behavior, but has proven difficult for neural networks to learn. In this paper we describe how to use Relation Networks (RNs) as a simple plug-and-play module to solve problems that fundamentally hinge on relational reasoning. We tested RN-augmented networks on three tasks: visual question answering using a challenging dataset called CLEVR, on which we achieve state-of-the-art, super-human performance; text-based question answering using the bAbI suite of tasks; and complex reasoning about dynamical physical systems. Then, using a curated dataset called Sort-of-CLEVR we show that powerful convolutional networks do not have a general capacity to solve relational questions, but can gain this capacity when augmented with RNs. Thus, by simply augmenting convolutions, LSTMs, and MLPs with RNs, we can remove computational burden from network components that are not well-suited to handle relational reasoning, reduce overall network complexity, and gain a general ability to reason about the relations between entities and their properties.

Scaling up visual category recognition to large numbers of classes remains challenging. A promising research direction is zero-shot learning, which does not require any training data to recognize new classes, but rather relies on some form of auxiliary information describing the new classes. Ultimately, this may allow to use textbook knowledge that humans employ to learn about new classes by transferring knowledge from classes they know well. The most successful zero-shot learning approaches currently require a particular type of auxiliary information - namely attribute annotations performed by humans - that is not readily available for most classes. Our goal is to circumvent this bottleneck by substituting such annotations by extracting multiple pieces of information from multiple unstructured text sources readily available on the web. To compensate for the weaker form of auxiliary information, we incorporate stronger supervision in the form of semantic part annotations on the classes from which we transfer knowledge. We achieve our goal by a joint embedding framework that maps multiple text parts as well as multiple semantic parts into a common space. Our results consistently and significantly improve on the state-of-the-art in zero-short recognition and retrieval.

The widespread integration of cameras in hand-held and head-worn devices and the ability to share content online enables a large and diverse visual capture of the world that millions of users build up collectively every day. We envision these images as well as associated meta information, such as GPS coordinates and timestamps, to form a collective visual memory that can be queried while automatically taking the ever-changing context of mobile users into account. As a first step towards this vision, in this work we present Xplore-M-Ego: a novel media retrieval system that allows users to query a dynamic database of images using spatio-temporal natural language queries. We evaluate our system using a new dataset of real image queries as well as through a usability study. One key finding is that there is a considerable amount of inter-user variability in the resolution of spatial relations in natural language utterances. We show that our system can cope with this variability using personalisation through an online learning-based retrieval formulation.

We address a question answering task on real-world images that is set up as a Visual Turing Test. By combining latest advances in image representation and natural language processing, we propose Neural-Image-QA, an end-to-end formulation to this problem for which all parts are trained jointly. In contrast to previous efforts, we are facing a multi-modal problem where the language output (answer) is conditioned on visual and natural language input (image and question). Our approach Neural-Image-QA doubles the performance of the previous best approach on this problem. We provide additional insights into the problem by analyzing how much information is contained only in the language part for which we provide a new human baseline. To study human consensus, which is related to the ambiguities inherent in this challenging task, we propose two novel metrics and collect additional answers which extends the original DAQUAR dataset to DAQUAR-Consensus.

From the early HMAX model to Spatial Pyramid Matching, spatial pooling has played an important role in visual recognition pipelines. By aggregating local statistics, it equips the recognition pipelines with a certain degree of robustness to translation and deformation yet preserving spatial information. Despite of its predominance in current recognition systems, we have seen little progress to fully adapt the pooling strategy to the task at hand. In this paper, we propose a flexible parameterization of the spatial pooling step and learn the pooling regions together with the classifier. We investigate a smoothness regularization term that in conjuncture with an efficient learning scheme makes learning scalable. Our framework can work with both popular pooling operators: sum-pooling and max-pooling. Finally, we show benefits of our approach for object recognition tasks based on visual words and higher level event recognition tasks based on object-bank features. In both cases, we improve over the hand-crafted spatial pooling step showing the importance of its adaptation to the task.

This paper describes CargoNet, a system of low-cost, micropower active sensor tags that seeks to bridge the current gap between wireless sensor networks and radio-frequency identification (RFID). CargoNet was aimed at applications in environmental monitoring at the crate and case level for supply-chain management and asset security. Custom-designed circuits and sensors were utilized to minimize power consumption and cost in a practical prototype. The CargoNet nodes are capable of asynchronous multimodal wakeup on exceptional events at extremely low power (Quasi-Passive Wakeup) with adjustable thresholds that adapt to dynamic environments. Accordingly, CargoNet has been seen to monitor, log, and report conditions inside a typical shipping crate while consuming under 25 microwatts of average power. To demonstrate the feasibility of the prototype system, several tests and deployments were conducted in the laboratory and aboard various transport conveyances.