Sjoerd van Steenkiste

Mostafa Dehghani, Josip Djolonga, Basil Mustafa et al. · deepmind

The scaling of Transformers has driven breakthrough capabilities for language models. At present, the largest large language models (LLMs) contain upwards of 100B parameters. Vision Transformers (ViT) have introduced the same architecture to image and video modelling, but these have not yet been successfully scaled to nearly the same degree; the largest dense ViT contains 4B parameters (Chen et al., 2022). We present a recipe for highly efficient and stable training of a 22B-parameter ViT (ViT-22B) and perform a wide variety of experiments on the resulting model. When evaluated on downstream tasks (often with a lightweight linear model on frozen features), ViT-22B demonstrates increasing performance with scale. We further observe other interesting benefits of scale, including an improved tradeoff between fairness and performance, state-of-the-art alignment to human visual perception in terms of shape/texture bias, and improved robustness. ViT-22B demonstrates the potential for "LLM-like" scaling in vision, and provides key steps towards getting there.

Mehdi S. M. Sajjadi, Daniel Duckworth, Aravindh Mahendran et al. · deepmind

A compositional understanding of the world in terms of objects and their geometry in 3D space is considered a cornerstone of human cognition. Facilitating the learning of such a representation in neural networks holds promise for substantially improving labeled data efficiency. As a key step in this direction, we make progress on the problem of learning 3D-consistent decompositions of complex scenes into individual objects in an unsupervised fashion. We introduce Object Scene Representation Transformer (OSRT), a 3D-centric model in which individual object representations naturally emerge through novel view synthesis. OSRT scales to significantly more complex scenes with larger diversity of objects and backgrounds than existing methods. At the same time, it is multiple orders of magnitude faster at compositional rendering thanks to its light field parametrization and the novel Slot Mixer decoder. We believe this work will not only accelerate future architecture exploration and scaling efforts, but it will also serve as a useful tool for both object-centric as well as neural scene representation learning communities.

Shravan Nayak, Kanishk Jain, Rabiul Awal et al. · eth-zurich

Foundation models and vision-language pre-training have notably advanced Vision Language Models (VLMs), enabling multimodal processing of visual and linguistic data. However, their performance has been typically assessed on general scene understanding - recognizing objects, attributes, and actions - rather than cultural comprehension. This study introduces CulturalVQA, a visual question-answering benchmark aimed at assessing VLM's geo-diverse cultural understanding. We curate a collection of 2,378 image-question pairs with 1-5 answers per question representing cultures from 11 countries across 5 continents. The questions probe understanding of various facets of culture such as clothing, food, drinks, rituals, and traditions. Benchmarking VLMs on CulturalVQA, including GPT-4V and Gemini, reveals disparity in their level of cultural understanding across regions, with strong cultural understanding capabilities for North America while significantly lower performance for Africa. We observe disparity in their performance across cultural facets too, with clothing, rituals, and traditions seeing higher performances than food and drink. These disparities help us identify areas where VLMs lack cultural understanding and demonstrate the potential of CulturalVQA as a comprehensive evaluation set for gauging VLM progress in understanding diverse cultures.

Jackson Petty, Sjoerd van Steenkiste, Ishita Dasgupta et al. · deepmind

To process novel sentences, language models (LMs) must generalize compositionally -- combine familiar elements in new ways. What aspects of a model's structure promote compositional generalization? Focusing on transformers, we test the hypothesis, motivated by theoretical and empirical work, that deeper transformers generalize more compositionally. Simply adding layers increases the total number of parameters; to address this confound between depth and size, we construct three classes of models which trade off depth for width such that the total number of parameters is kept constant (41M, 134M and 374M parameters). We pretrain all models as LMs and fine-tune them on tasks that test for compositional generalization. We report three main conclusions: (1) after fine-tuning, deeper models generalize more compositionally than shallower models do, but the benefit of additional layers diminishes rapidly; (2) within each family, deeper models show better language modeling performance, but returns are similarly diminishing; (3) the benefits of depth for compositional generalization cannot be attributed solely to better performance on language modeling. Because model latency is approximately linear in the number of layers, these results lead us to the recommendation that, with a given total parameter budget, transformers can be made shallower than is typical without sacrificing performance.

Mihir Prabhudesai, Anirudh Goyal, Sujoy Paul et al. · cmu

Current visual detectors, though impressive within their training distribution, often fail to parse out-of-distribution scenes into their constituent entities. Recent test-time adaptation methods use auxiliary self-supervised losses to adapt the network parameters to each test example independently and have shown promising results towards generalization outside the training distribution for the task of image classification. In our work, we find evidence that these losses are insufficient for the task of scene decomposition, without also considering architectural inductive biases. Recent slot-centric generative models attempt to decompose scenes into entities in a self-supervised manner by reconstructing pixels. Drawing upon these two lines of work, we propose Slot-TTA, a semi-supervised slot-centric scene decomposition model that at test time is adapted per scene through gradient descent on reconstruction or cross-view synthesis objectives. We evaluate Slot-TTA across multiple input modalities, images or 3D point clouds, and show substantial out-of-distribution performance improvements against state-of-the-art supervised feed-forward detectors, and alternative test-time adaptation methods.

Anand Gopalakrishnan, Kazuki Irie, Jürgen Schmidhuber et al.

The discovery of reusable sub-routines simplifies decision-making and planning in complex reinforcement learning problems. Previous approaches propose to learn such temporal abstractions in a purely unsupervised fashion through observing state-action trajectories gathered from executing a policy. However, a current limitation is that they process each trajectory in an entirely sequential manner, which prevents them from revising earlier decisions about sub-routine boundary points in light of new incoming information. In this work we propose SloTTAr, a fully parallel approach that integrates sequence processing Transformers with a Slot Attention module and adaptive computation for learning about the number of such sub-routines in an unsupervised fashion. We demonstrate how SloTTAr is capable of outperforming strong baselines in terms of boundary point discovery, even for sequences containing variable amounts of sub-routines, while being up to 7x faster to train on existing benchmarks.

Aditya Ramesh, Louis Kirsch, Sjoerd van Steenkiste et al.

Efficient exploration in reinforcement learning is a challenging problem commonly addressed through intrinsic rewards. Recent prominent approaches are based on state novelty or variants of artificial curiosity. However, directly applying them to partially observable environments can be ineffective and lead to premature dissipation of intrinsic rewards. Here we propose random curiosity with general value functions (RC-GVF), a novel intrinsic reward function that draws upon connections between these distinct approaches. Instead of using only the current observation's novelty or a curiosity bonus for failing to predict precise environment dynamics, RC-GVF derives intrinsic rewards through predicting temporally extended general value functions. We demonstrate that this improves exploration in a hard-exploration diabolical lock problem. Furthermore, RC-GVF significantly outperforms previous methods in the absence of ground-truth episodic counts in the partially observable MiniGrid environments. Panoramic observations on MiniGrid further boost RC-GVF's performance such that it is competitive to baselines exploiting privileged information in form of episodic counts.

Gamaleldin F. Elsayed, Aravindh Mahendran, Sjoerd van Steenkiste et al.

The visual world can be parsimoniously characterized in terms of distinct entities with sparse interactions. Discovering this compositional structure in dynamic visual scenes has proven challenging for end-to-end computer vision approaches unless explicit instance-level supervision is provided. Slot-based models leveraging motion cues have recently shown great promise in learning to represent, segment, and track objects without direct supervision, but they still fail to scale to complex real-world multi-object videos. In an effort to bridge this gap, we take inspiration from human development and hypothesize that information about scene geometry in the form of depth signals can facilitate object-centric learning. We introduce SAVi++, an object-centric video model which is trained to predict depth signals from a slot-based video representation. By further leveraging best practices for model scaling, we are able to train SAVi++ to segment complex dynamic scenes recorded with moving cameras, containing both static and moving objects of diverse appearance on naturalistic backgrounds, without the need for segmentation supervision. Finally, we demonstrate that by using sparse depth signals obtained from LiDAR, SAVi++ is able to learn emergent object segmentation and tracking from videos in the real-world Waymo Open dataset.

Ondrej Biza, Sjoerd van Steenkiste, Mehdi S. M. Sajjadi et al.

Automatically discovering composable abstractions from raw perceptual data is a long-standing challenge in machine learning. Recent slot-based neural networks that learn about objects in a self-supervised manner have made exciting progress in this direction. However, they typically fall short at adequately capturing spatial symmetries present in the visual world, which leads to sample inefficiency, such as when entangling object appearance and pose. In this paper, we present a simple yet highly effective method for incorporating spatial symmetries via slot-centric reference frames. We incorporate equivariance to per-object pose transformations into the attention and generation mechanism of Slot Attention by translating, scaling, and rotating position encodings. These changes result in little computational overhead, are easy to implement, and can result in large gains in terms of data efficiency and overall improvements to object discovery. We evaluate our method on a wide range of synthetic object discovery benchmarks namely CLEVR, Tetrominoes, CLEVRTex, Objects Room and MultiShapeNet, and show promising improvements on the challenging real-world Waymo Open dataset.

Jiao Sun, Deqing Fu, Yushi Hu et al.

Despite their wide-spread success, Text-to-Image models (T2I) still struggle to produce images that are both aesthetically pleasing and faithful to the user's input text. We introduce DreamSync, a model-agnostic training algorithm by design that improves T2I models to be faithful to the text input. DreamSync builds off a recent insight from TIFA's evaluation framework -- that large vision-language models (VLMs) can effectively identify the fine-grained discrepancies between generated images and the text inputs. DreamSync uses this insight to train T2I models without any labeled data; it improves T2I models using its own generations. First, it prompts the model to generate several candidate images for a given input text. Then, it uses two VLMs to select the best generation: a Visual Question Answering model that measures the alignment of generated images to the text, and another that measures the generation's aesthetic quality. After selection, we use LoRA to iteratively finetune the T2I model to guide its generation towards the selected best generations. DreamSync does not need any additional human annotation. model architecture changes, or reinforcement learning. Despite its simplicity, DreamSync improves both the semantic alignment and aesthetic appeal of two diffusion-based T2I models, evidenced by multiple benchmarks (+1.7% on TIFA, +2.9% on DSG1K, +3.4% on VILA aesthetic) and human evaluation.

Allan Jabri, Sjoerd van Steenkiste, Emiel Hoogeboom et al.

Recent progress in 3D scene understanding enables scalable learning of representations across large datasets of diverse scenes. As a consequence, generalization to unseen scenes and objects, rendering novel views from just a single or a handful of input images, and controllable scene generation that supports editing, is now possible. However, training jointly on a large number of scenes typically compromises rendering quality when compared to single-scene optimized models such as NeRFs. In this paper, we leverage recent progress in diffusion models to equip 3D scene representation learning models with the ability to render high-fidelity novel views, while retaining benefits such as object-level scene editing to a large degree. In particular, we propose DORSal, which adapts a video diffusion architecture for 3D scene generation conditioned on frozen object-centric slot-based representations of scenes. On both complex synthetic multi-object scenes and on the real-world large-scale Street View dataset, we show that DORSal enables scalable neural rendering of 3D scenes with object-level editing and improves upon existing approaches.

Maximilian Seitzer, Sjoerd van Steenkiste, Thomas Kipf et al.

Visual understanding of the world goes beyond the semantics and flat structure of individual images. In this work, we aim to capture both the 3D structure and dynamics of real-world scenes from monocular real-world videos. Our Dynamic Scene Transformer (DyST) model leverages recent work in neural scene representation to learn a latent decomposition of monocular real-world videos into scene content, per-view scene dynamics, and camera pose. This separation is achieved through a novel co-training scheme on monocular videos and our new synthetic dataset DySO. DyST learns tangible latent representations for dynamic scenes that enable view generation with separate control over the camera and the content of the scene.

Jackson Petty, Sjoerd van Steenkiste, Tal Linzen

Large language models are increasingly trained on corpora containing both natural language and non-linguistic data like source code. Aside from aiding programming-related tasks, anecdotal evidence suggests that including code in pretraining corpora may improve performance on other, unrelated tasks, yet to date no work has been able to establish a causal connection by controlling between language and code data. Here we do just this. We pretrain language models on datasets which interleave natural language and code in two different settings: additive, in which the total volume of data seen during pretraining is held constant; and competitive, in which the volume of language data is held constant. We study how the pretraining mixture affects performance on (a) a diverse collection of tasks included in the BigBench benchmark, and (b) compositionality, measured by generalization accuracy on semantic parsing and syntactic transformations. We find that pretraining on higher proportions of code improves performance on compositional tasks involving structured output (like semantic parsing), and mathematics. Conversely, increase code mixture can harm performance on other tasks, including on tasks that requires sensitivity to linguistic structure such as syntax or morphology, and tasks measuring real-world knowledge.

Tiwalayo Eisape, MH Tessler, Ishita Dasgupta et al.

A central component of rational behavior is logical inference: the process of determining which conclusions follow from a set of premises. Psychologists have documented several ways in which humans' inferences deviate from the rules of logic. Do language models, which are trained on text generated by humans, replicate such human biases, or are they able to overcome them? Focusing on the case of syllogisms -- inferences from two simple premises -- we show that, within the PaLM2 family of transformer language models, larger models are more logical than smaller ones, and also more logical than humans. At the same time, even the largest models make systematic errors, some of which mirror human reasoning biases: they show sensitivity to the (irrelevant) ordering of the variables in the syllogism, and draw confident but incorrect inferences from particular syllogisms (syllogistic fallacies). Overall, we find that language models often mimic the human biases included in their training data, but are able to overcome them in some cases.

João Carreira, Dilara Gokay, Michael King et al.

Scaling has not yet been convincingly demonstrated for pure self-supervised learning from video. However, prior work has focused evaluations on semantic-related tasks $\unicode{x2013}$ action classification, ImageNet classification, etc. In this paper we focus on evaluating self-supervised learning on non-semantic vision tasks that are more spatial (3D) and temporal (+1D = 4D), such as camera pose estimation, point and object tracking, and depth estimation. We show that by learning from very large video datasets, masked auto-encoding (MAE) with transformer video models actually scales, consistently improving performance on these 4D tasks, as model size increases from 20M all the way to the largest by far reported self-supervised video model $\unicode{x2013}$ 22B parameters. Rigorous apples-to-apples comparison with many recent image and video models demonstrates the benefits of scaling 4D representations. Pretrained models are available at https://github.com/google-deepmind/representations4d .

Kelsey Allen, Carl Doersch, Guangyao Zhou et al.

A current limitation of video generative video models is that they generate plausible looking frames, but poor motion -- an issue that is not well captured by FVD and other popular methods for evaluating generated videos. Here we go beyond FVD by developing a metric which better measures plausible object interactions and motion. Our novel approach is based on auto-encoding point tracks and yields motion features that can be used to not only compare distributions of videos (as few as one generated and one ground truth, or as many as two datasets), but also for evaluating motion of single videos. We show that using point tracks instead of pixel reconstruction or action recognition features results in a metric which is markedly more sensitive to temporal distortions in synthetic data, and can predict human evaluations of temporal consistency and realism in generated videos obtained from open-source models better than a wide range of alternatives. We also show that by using a point track representation, we can spatiotemporally localize generative video inconsistencies, providing extra interpretability of generated video errors relative to prior work. An overview of the results and link to the code can be found on the project page: http://trajan-paper.github.io.

Linlu Qiu, Fei Sha, Kelsey Allen et al.

Artificial intelligence systems based on large language models (LLMs) are increasingly used as agents that interact with users and with the world. To do so successfully, LLMs need to construct internal representations of the world and form probabilistic beliefs about those representations. To provide a user with personalized recommendations, for example, the LLM needs to gradually infer the user's preferences, over the course of multiple interactions. To evaluate whether contemporary LLMs are able to do so, we use the Bayesian inference framework from probability theory, which lays out the optimal way to update an agent's beliefs as it receives new information. We first show that LLMs do not update their beliefs as expected from the Bayesian framework, and that consequently their predictions do not improve as expected as more information becomes available. To address this issue, we teach the LLMs to reason in a Bayesian manner by training them to mimic the predictions of the normative Bayesian model. We find that this approach not only significantly improves the LLM's performance on the particular recommendation task it is trained on, but also enables generalization to other tasks. This suggests that this method teaches the LLM to better approximate Bayesian reasoning. More generally, our results indicate that LLMs can effectively learn reasoning skills from examples and generalize those skills to new domains.

Sjoerd van Steenkiste, Daniel Zoran, Yi Yang et al.

Current vision models typically maintain a fixed correspondence between their representation structure and image space. Each layer comprises a set of tokens arranged "on-the-grid," which biases patches or tokens to encode information at a specific spatio(-temporal) location. In this work we present Moving Off-the-Grid (MooG), a self-supervised video representation model that offers an alternative approach, allowing tokens to move "off-the-grid" to better enable them to represent scene elements consistently, even as they move across the image plane through time. By using a combination of cross-attention and positional embeddings we disentangle the representation structure and image structure. We find that a simple self-supervised objective--next frame prediction--trained on video data, results in a set of latent tokens which bind to specific scene structures and track them as they move. We demonstrate the usefulness of MooG's learned representation both qualitatively and quantitatively by training readouts on top of the learned representation on a variety of downstream tasks. We show that MooG can provide a strong foundation for different vision tasks when compared to "on-the-grid" baselines.

Shravan Nayak, Mehar Bhatia, Xiaofeng Zhang et al. · eth-zurich

The increasing ubiquity of text-to-image (T2I) models as tools for visual content generation raises concerns about their ability to accurately represent diverse cultural contexts -- where missed cues can stereotype communities and undermine usability. In this work, we present the first study to systematically quantify the alignment of T2I models and evaluation metrics with respect to both explicit (stated) as well as implicit (unstated, implied by the prompt's cultural context) cultural expectations. To this end, we introduce CulturalFrames, a novel benchmark designed for rigorous human evaluation of cultural representation in visual generations. Spanning 10 countries and 5 socio-cultural domains, CulturalFrames comprises 983 prompts, 3637 corresponding images generated by 4 state-of-the-art T2I models, and over 10k detailed human annotations. We find that across models and countries, cultural expectations are missed an average of 44% of the time. Among these failures, explicit expectations are missed at a surprisingly high average rate of 68%, while implicit expectation failures are also significant, averaging 49%. Furthermore, we show that existing T2I evaluation metrics correlate poorly with human judgments of cultural alignment, irrespective of their internal reasoning. Collectively, our findings expose critical gaps, provide a concrete testbed, and outline actionable directions for developing culturally informed T2I models and metrics that improve global usability.

Alejandro Escontrela, Shrinu Kushagra, Sjoerd van Steenkiste et al.

Amazing progress has been made in controllable generative modeling, especially over the last few years. However, some challenges remain. One of them is precise and iterative object editing. In many of the current methods, trying to edit the generated image (for example, changing the color of a particular object in the scene or changing the background while keeping other elements unchanged) by changing the conditioning signals often leads to unintended global changes in the scene. In this work, we take the first steps to address the above challenges. Taking inspiration from the Universal Scene Descriptor (USD) standard developed in the computer graphics community, we introduce the "Neural Universal Scene Descriptor" or Neural USD. In this framework, we represent scenes and objects in a structured, hierarchical manner. This accommodates diverse signals, minimizes model-specific constraints, and enables per-object control over appearance, geometry, and pose. We further apply a fine-tuning approach which ensures that the above control signals are disentangled from one another. We evaluate several design considerations for our framework, demonstrating how Neural USD enables iterative and incremental workflows. More information at: https://escontrela.me/neural_usd .

Rishabh Kabra, Drew A. Hudson, Sjoerd van Steenkiste et al.

We introduce a hierarchical probabilistic approach to go from a 2D image to multiview 3D: a diffusion "prior" predicts the unseen 3D geometry, which then conditions a diffusion "decoder" to generate novel views of the subject. We use a pointmap-based geometric representation to coordinate the generation of multiple target views simultaneously. We construct a predictable distribution of geometric features per target view to enable learnability across examples, and generalization to arbitrary inputs images. Our modular, geometry-driven approach to novel-view synthesis (called "unPIC") beats competing baselines such as CAT3D, EscherNet, Free3D, and One-2-3-45 on held-out objects from ObjaverseXL, as well as unseen real-world objects from Google Scanned Objects, Amazon Berkeley Objects, and the Digital Twin Catalog.

Ziyi Wu, Yulia Rubanova, Rishabh Kabra et al.

We address the problem of multi-object 3D pose control in image diffusion models. Instead of conditioning on a sequence of text tokens, we propose to use a set of per-object representations, Neural Assets, to control the 3D pose of individual objects in a scene. Neural Assets are obtained by pooling visual representations of objects from a reference image, such as a frame in a video, and are trained to reconstruct the respective objects in a different image, e.g., a later frame in the video. Importantly, we encode object visuals from the reference image while conditioning on object poses from the target frame. This enables learning disentangled appearance and pose features. Combining visual and 3D pose representations in a sequence-of-tokens format allows us to keep the text-to-image architecture of existing models, with Neural Assets in place of text tokens. By fine-tuning a pre-trained text-to-image diffusion model with this information, our approach enables fine-grained 3D pose and placement control of individual objects in a scene. We further demonstrate that Neural Assets can be transferred and recomposed across different scenes. Our model achieves state-of-the-art multi-object editing results on both synthetic 3D scene datasets, as well as two real-world video datasets (Objectron, Waymo Open).

Roland S. Zimmermann, Sjoerd van Steenkiste, Mehdi S. M. Sajjadi et al.

Self-supervised methods for learning object-centric representations have recently been applied successfully to various datasets. This progress is largely fueled by slot-based methods, whose ability to cluster visual scenes into meaningful objects holds great promise for compositional generalization and downstream learning. In these methods, the number of slots (clusters) $K$ is typically chosen to match the number of ground-truth objects in the data, even though this quantity is unknown in real-world settings. Indeed, the sensitivity of slot-based methods to $K$, and how this affects their learned correspondence to objects in the data has largely been ignored in the literature. In this work, we address this issue through a systematic study of slot-based methods. We propose using analogs to precision and recall based on the Adjusted Rand Index to accurately quantify model behavior over a large range of $K$. We find that, especially during training, incorrect choices of $K$ do not yield the desired object decomposition and, in fact, cause substantial oversegmentation or merging of separate objects (undersegmentation). We demonstrate that the choice of the objective function and incorporating instance-level annotations can moderately mitigate this behavior while still falling short of fully resolving this issue. Indeed, we show how this issue persists across multiple methods and datasets and stress its importance for future slot-based models.

Klaus Greff, Sjoerd van Steenkiste, Jürgen Schmidhuber

Contemporary neural networks still fall short of human-level generalization, which extends far beyond our direct experiences. In this paper, we argue that the underlying cause for this shortcoming is their inability to dynamically and flexibly bind information that is distributed throughout the network. This binding problem affects their capacity to acquire a compositional understanding of the world in terms of symbol-like entities (like objects), which is crucial for generalizing in predictable and systematic ways. To address this issue, we propose a unifying framework that revolves around forming meaningful entities from unstructured sensory inputs (segregation), maintaining this separation of information at a representational level (representation), and using these entities to construct new inferences, predictions, and behaviors (composition). Our analysis draws inspiration from a wealth of research in neuroscience and cognitive psychology, and surveys relevant mechanisms from the machine learning literature, to help identify a combination of inductive biases that allow symbolic information processing to emerge naturally in neural networks. We believe that a compositional approach to AI, in terms of grounded symbol-like representations, is of fundamental importance for realizing human-level generalization, and we hope that this paper may contribute towards that goal as a reference and inspiration.

Anand Gopalakrishnan, Sjoerd van Steenkiste, Jürgen Schmidhuber

We propose PermaKey, a novel approach to representation learning based on object keypoints. It leverages the predictability of local image regions from spatial neighborhoods to identify salient regions that correspond to object parts, which are then converted to keypoints. Unlike prior approaches, it utilizes predictability to discover object keypoints, an intrinsic property of objects. This ensures that it does not overly bias keypoints to focus on characteristics that are not unique to objects, such as movement, shape, colour etc. We demonstrate the efficacy of PermaKey on Atari where it learns keypoints corresponding to the most salient object parts and is robust to certain visual distractors. Further, on downstream RL tasks in the Atari domain we demonstrate how agents equipped with our keypoints outperform those using competing alternatives, even on challenging environments with moving backgrounds or distractor objects.

Aleksandar Stanić, Sjoerd van Steenkiste, Jürgen Schmidhuber

Common-sense physical reasoning in the real world requires learning about the interactions of objects and their dynamics. The notion of an abstract object, however, encompasses a wide variety of physical objects that differ greatly in terms of the complex behaviors they support. To address this, we propose a novel approach to physical reasoning that models objects as hierarchies of parts that may locally behave separately, but also act more globally as a single whole. Unlike prior approaches, our method learns in an unsupervised fashion directly from raw visual images to discover objects, parts, and their relations. It explicitly distinguishes multiple levels of abstraction and improves over a strong baseline at modeling synthetic and real-world videos.

Róbert Csordás, Sjoerd van Steenkiste, Jürgen Schmidhuber

Neural networks (NNs) whose subnetworks implement reusable functions are expected to offer numerous advantages, including compositionality through efficient recombination of functional building blocks, interpretability, preventing catastrophic interference, etc. Understanding if and how NNs are modular could provide insights into how to improve them. Current inspection methods, however, fail to link modules to their functionality. In this paper, we present a novel method based on learning binary weight masks to identify individual weights and subnets responsible for specific functions. Using this powerful tool, we contribute an extensive study of emerging modularity in NNs that covers several standard architectures and datasets. We demonstrate how common NNs fail to reuse submodules and offer new insights into the related issue of systematic generalization on language tasks.

Louis Kirsch, Sjoerd van Steenkiste, Jürgen Schmidhuber

Biological evolution has distilled the experiences of many learners into the general learning algorithms of humans. Our novel meta reinforcement learning algorithm MetaGenRL is inspired by this process. MetaGenRL distills the experiences of many complex agents to meta-learn a low-complexity neural objective function that decides how future individuals will learn. Unlike recent meta-RL algorithms, MetaGenRL can generalize to new environments that are entirely different from those used for meta-training. In some cases, it even outperforms human-engineered RL algorithms. MetaGenRL uses off-policy second-order gradients during meta-training that greatly increase its sample efficiency.

Sjoerd van Steenkiste, Klaus Greff, Jürgen Schmidhuber

In order to meet the diverse challenges in solving many real-world problems, an intelligent agent has to be able to dynamically construct a model of its environment. Objects facilitate the modular reuse of prior knowledge and the combinatorial construction of such models. In this work, we argue that dynamically bound features (objects) do not simply emerge in connectionist models of the world. We identify several requirements that need to be fulfilled in overcoming this limitation and highlight corresponding inductive biases.

Sjoerd van Steenkiste, Francesco Locatello, Jürgen Schmidhuber et al.

A disentangled representation encodes information about the salient factors of variation in the data independently. Although it is often argued that this representational format is useful in learning to solve many real-world down-stream tasks, there is little empirical evidence that supports this claim. In this paper, we conduct a large-scale study that investigates whether disentangled representations are more suitable for abstract reasoning tasks. Using two new tasks similar to Raven's Progressive Matrices, we evaluate the usefulness of the representations learned by 360 state-of-the-art unsupervised disentanglement models. Based on these representations, we train 3600 abstract reasoning models and observe that disentangled representations do in fact lead to better down-stream performance. In particular, they enable quicker learning using fewer samples.

Thomas Unterthiner, Sjoerd van Steenkiste, Karol Kurach et al.

Recent advances in deep generative models have lead to remarkable progress in synthesizing high quality images. Following their successful application in image processing and representation learning, an important next step is to consider videos. Learning generative models of video is a much harder task, requiring a model to capture the temporal dynamics of a scene, in addition to the visual presentation of objects. While recent attempts at formulating generative models of video have had some success, current progress is hampered by (1) the lack of qualitative metrics that consider visual quality, temporal coherence, and diversity of samples, and (2) the wide gap between purely synthetic video data sets and challenging real-world data sets in terms of complexity. To this extent we propose Fréchet Video Distance (FVD), a new metric for generative models of video, and StarCraft 2 Videos (SCV), a benchmark of game play from custom starcraft 2 scenarios that challenge the current capabilities of generative models of video. We contribute a large-scale human study, which confirms that FVD correlates well with qualitative human judgment of generated videos, and provide initial benchmark results on SCV.

Sjoerd van Steenkiste, Karol Kurach, Jürgen Schmidhuber et al.

Deep generative models seek to recover the process with which the observed data was generated. They may be used to synthesize new samples or to subsequently extract representations. Successful approaches in the domain of images are driven by several core inductive biases. However, a bias to account for the compositional way in which humans structure a visual scene in terms of objects has frequently been overlooked. In this work, we investigate object compositionality as an inductive bias for Generative Adversarial Networks (GANs). We present a minimal modification of a standard generator to incorporate this inductive bias and find that it reliably learns to generate images as compositions of objects. Using this general design as a backbone, we then propose two useful extensions to incorporate dependencies among objects and background. We extensively evaluate our approach on several multi-object image datasets and highlight the merits of incorporating structure for representation learning purposes. In particular, we find that our structured GANs are better at generating multi-object images that are more faithful to the reference distribution. More so, we demonstrate how, by leveraging the structure of the learned generative process, one can `invert' the learned generative model to perform unsupervised instance segmentation. On the challenging CLEVR dataset, it is shown how our approach is able to improve over other recent purely unsupervised object-centric approaches to image generation.

Sjoerd van Steenkiste, Michael Chang, Klaus Greff et al.

Common-sense physical reasoning is an essential ingredient for any intelligent agent operating in the real-world. For example, it can be used to simulate the environment, or to infer the state of parts of the world that are currently unobserved. In order to match real-world conditions this causal knowledge must be learned without access to supervised data. To address this problem we present a novel method that learns to discover objects and model their physical interactions from raw visual images in a purely \emph{unsupervised} fashion. It incorporates prior knowledge about the compositional nature of human perception to factor interactions between object-pairs and learn efficiently. On videos of bouncing balls we show the superior modelling capabilities of our method compared to other unsupervised neural approaches that do not incorporate such prior knowledge. We demonstrate its ability to handle occlusion and show that it can extrapolate learned knowledge to scenes with different numbers of objects.

Klaus Greff, Sjoerd van Steenkiste, Jürgen Schmidhuber

Many real world tasks such as reasoning and physical interaction require identification and manipulation of conceptual entities. A first step towards solving these tasks is the automated discovery of distributed symbol-like representations. In this paper, we explicitly formalize this problem as inference in a spatial mixture model where each component is parametrized by a neural network. Based on the Expectation Maximization framework we then derive a differentiable clustering method that simultaneously learns how to group and represent individual entities. We evaluate our method on the (sequential) perceptual grouping task and find that it is able to accurately recover the constituent objects. We demonstrate that the learned representations are useful for next-step prediction.