In this paper, we question if self-supervised learning provides new properties to Vision Transformer (ViT) that stand out compared to convolutional networks (convnets). Beyond the fact that adapting self-supervised methods to this architecture works particularly well, we make the following observations: first, self-supervised ViT features contain explicit information about the semantic segmentation of an image, which does not emerge as clearly with supervised ViTs, nor with convnets. Second, these features are also excellent k-NN classifiers, reaching 78.3% top-1 on ImageNet with a small ViT. Our study also underlines the importance of momentum encoder, multi-crop training, and the use of small patches with ViTs. We implement our findings into a simple self-supervised method, called DINO, which we interpret as a form of self-distillation with no labels. We show the synergy between DINO and ViTs by achieving 80.1% top-1 on ImageNet in linear evaluation with ViT-Base.
This presentation addresses the problem of reconstructing a high-resolution image from multiple lower-resolution snapshots captured from slightly different viewpoints in space and time. Key challenges for solving this problem include (i) aligning the input pictures with sub-pixel accuracy, (ii) handling raw (noisy) images for maximal faithfulness to native camera data, and (iii) designing/learning an image prior (regularizer) well suited to the task. We address these three challenges with a hybrid algorithm building on the insight from Wronski et al. that aliasing is an ally in this setting, with parameters that can be learned end to end, while retaining the interpretability of classical approaches to inverse problems. The effectiveness of our approach is demonstrated on synthetic and real image bursts, setting a new state of the art on several benchmarks and delivering excellent qualitative results on real raw bursts captured by smartphones and prosumer cameras.
Unsupervised image representations have significantly reduced the gap with supervised pretraining, notably with the recent achievements of contrastive learning methods. These contrastive methods typically work online and rely on a large number of explicit pairwise feature comparisons, which is computationally challenging. In this paper, we propose an online algorithm, SwAV, that takes advantage of contrastive methods without requiring to compute pairwise comparisons. Specifically, our method simultaneously clusters the data while enforcing consistency between cluster assignments produced for different augmentations (or views) of the same image, instead of comparing features directly as in contrastive learning. Simply put, we use a swapped prediction mechanism where we predict the cluster assignment of a view from the representation of another view. Our method can be trained with large and small batches and can scale to unlimited amounts of data. Compared to previous contrastive methods, our method is more memory efficient since it does not require a large memory bank or a special momentum network. In addition, we also propose a new data augmentation strategy, multi-crop, that uses a mix of views with different resolutions in place of two full-resolution views, without increasing the memory or compute requirements much. We validate our findings by achieving 75.3% top-1 accuracy on ImageNet with ResNet-50, as well as surpassing supervised pretraining on all the considered transfer tasks.
We introduce a general framework for designing and learning neural networks whose forward passes can be interpreted as solving convex optimization problems, and whose architectures are derived from an optimization algorithm. We focus on non-cooperative convex games, solved by local agents represented by the nodes of a graph and interacting through regularization functions. This approach is appealing for solving imaging problems, as it allows the use of classical image priors within deep models that are trainable end to end. The priors used in this presentation include variants of total variation, Laplacian regularization, sparse coding on learned dictionaries, and non-local self similarities. Our models are parameter efficient and fully interpretable, and our experiments demonstrate their effectiveness on a large diversity of tasks ranging from image denoising and compressed sensing for fMRI to dense stereo matching.
We introduce a kernel for sets of features based on an optimal transport distance, along with an explicit embedding function. Our approach addresses the problem of feature aggregation, or pooling, for sets that exhibit long-range dependencies between their members. More precisely, our embedding aggregates the features of a given set according to the transport plan between the set and a reference shared across the data set. Unlike traditional hand-crafted kernels, our embedding can be optimized for a specific task or data set. It also has a natural connection to attention mechanisms in neural networks, which are commonly used to deal with sets, yet requires less data. Our embedding is particularly suited for biological sequence classification tasks and shows promising results for natural language sequences. We provide an implementation of our embedding that can be used alone or as a module in larger learning models. Our code is freely available at https://github.com/claying/OTK.
Counterfactual reasoning from logged data has become increasingly important for a large range of applications such as web advertising or healthcare. In this paper, we address the problem of counterfactual risk minimization for learning a stochastic policy with a continuous action space. Whereas previous works have mostly focused on deriving statistical estimators with importance sampling, we show that the optimization perspective is equally important for solving the resulting nonconvex optimization problems.Specifically, we demonstrate the benefits of proximal point algorithms and soft-clipping estimators which are more amenable to gradient-based optimization than classical hard clipping. We propose multiple synthetic, yet realistic, evaluation setups, and we release a new large-scale dataset based on web advertising data for this problem that is crucially missing public benchmarks.
Popular approaches for few-shot classification consist of first learning a generic data representation based on a large annotated dataset, before adapting the representation to new classes given only a few labeled samples. In this work, we propose a new strategy based on feature selection, which is both simpler and more effective than previous feature adaptation approaches. First, we obtain a universal representation by training a set of semantically different feature extractors. Then, given a few-shot learning task, we use our universal feature bank to automatically select the most relevant representations. We show that a simple non-parametric classifier built on top of such features produces high accuracy and generalizes to domains never seen during training, which leads to state-of-the-art results on MetaDataset and improved accuracy on mini-ImageNet.
We introduce a family of multilayer graph kernels and establish new links between graph convolutional neural networks and kernel methods. Our approach generalizes convolutional kernel networks to graph-structured data, by representing graphs as a sequence of kernel feature maps, where each node carries information about local graph substructures. On the one hand, the kernel point of view offers an unsupervised, expressive, and easy-to-regularize data representation, which is useful when limited samples are available. On the other hand, our model can also be trained end-to-end on large-scale data, leading to new types of graph convolutional neural networks. We show that our method achieves competitive performance on several graph classification benchmarks, while offering simple model interpretation. Our code is freely available at https://github.com/claying/GCKN.