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.

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.

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, which enables learning disentangled appearance and position features. Combining visual and 3D pose representations in a sequence-of-tokens format allows us to keep the text-to-image interface 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).

We introduce the GANsformer, a novel and efficient type of transformer, and explore it for the task of visual generative modeling. The network employs a bipartite structure that enables long-range interactions across the image, while maintaining computation of linear efficiency, that can readily scale to high-resolution synthesis. It iteratively propagates information from a set of latent variables to the evolving visual features and vice versa, to support the refinement of each in light of the other and encourage the emergence of compositional representations of objects and scenes. In contrast to the classic transformer architecture, it utilizes multiplicative integration that allows flexible region-based modulation, and can thus be seen as a generalization of the successful StyleGAN network. We demonstrate the model’s strength and robustness through a careful evaluation over a range of datasets, from simulated multi-object environments to rich real-world indoor and outdoor scenes, showing it achieves state-of-the-art results in terms of image quality and diversity, while enjoying fast learning and better data-efficiency. Further qualitative and quantitative experiments offer us an insight into the model’s inner workings, revealing improved interpretability and stronger disentanglement, and illustrating the benefits and efficacy of our approach. An implementation of the model is available at https://github.com/dorarad/gansformer.

We introduce Sentence-level Language Modeling, a new pre-training objective for learning a discourse language representation in a fully self-supervised manner.Recent pre-training methods in NLP focus on learning either bottom or top-level language representations: contextualized word representations derived from language model objectives at one extreme and a whole sequence representation learned by order classification of two given textual segments at the other.However, these models are not directly encouraged to capture representations of intermediate-size structures that exist in natural languages such as sentences and the relationships among them.To that end, we propose a new approach to encourage learning of a contextualized sentence-level representation by shuffling the sequence of input sentences and training a hierarchical transformer model to reconstruct the original ordering.Through experiments on downstream tasks such as GLUE, SQuAD, and DiscoEval, we show that this feature of our model improves the performance of the original BERT by large margins.

We introduce GQA, a new dataset for real-world visual reasoning and compositional question answering, seeking to address key shortcomings of previous VQA datasets. We have developed a strong and robust question engine that leverages Visual Genome scene graph structures to create 22M diverse reasoning questions, which all come with functional programs that represent their semantics. We use the programs to gain tight control over the answer distribution and present a new tunable smoothing technique to mitigate question biases. Accompanying the dataset is a suite of new metrics that evaluate essential qualities such as consistency, grounding and plausibility. A careful analysis is performed for baselines as well as state-of-the-art models, providing fine-grained results for different question types and topologies. Whereas a blind LSTM obtains a mere 42.1%, and strong VQA models achieve 54.1%, human performance tops at 89.3%, offering ample opportunity for new research to explore. We hope GQA will provide an enabling resource for the next generation of models with enhanced robustness, improved consistency, and deeper semantic understanding of vision and language.

We introduce the Neural State Machine, seeking to bridge the gap between the neural and symbolic views of AI and integrate their complementary strengths for the task of visual reasoning. Given an image, we first predict a probabilistic graph that represents its underlying semantics and serves as a structured world model. Then, we perform sequential reasoning over the graph, iteratively traversing its nodes to answer a given question or draw a new inference. In contrast to most neural architectures that are designed to closely interact with the raw sensory data, our model operates instead in an abstract latent space, by transforming both the visual and linguistic modalities into semantic concept-based representations, thereby achieving enhanced transparency and modularity. We evaluate our model on VQA-CP and GQA, two recent VQA datasets that involve compositionality, multi-step inference and diverse reasoning skills, achieving state-of-the-art results in both cases. We provide further experiments that illustrate the model's strong generalization capacity across multiple dimensions, including novel compositions of concepts, changes in the answer distribution, and unseen linguistic structures, demonstrating the qualities and efficacy of our approach.