In the past few years, we have witnessed remarkable breakthroughs in self-supervised
representation learning. Despite the success and adoption of representations learned …

Abstract We present Momentum Contrast (MoCo) for unsupervised visual representation
learning. From a perspective on contrastive learning as dictionary look-up, we build a …

Self-supervised learning aims to learn representations from the data itself without explicit
manual supervision. Existing efforts ignore a crucial aspect of self-supervised learning-the …

We present an extension to masked autoencoders (MAE) which improves on the
representations learnt by the model by explicitly encouraging the learning of higher scene …

Fine-grained and instance-level recognition methods are commonly trained and evaluated
on specific domains, in a model per domain scenario. Such an approach, however, is …

The success of deep neural networks often relies on a large amount of labeled examples,
which can be difficult to obtain in many real scenarios. To address this challenge …

Contrastive self-supervised learning has emerged as a promising approach to unsupervised
visual representation learning. In general, these methods learn global (image-level) …

Self-supervised learning based on instance discrimination has shown remarkable progress.
In particular, contrastive learning, which regards each image as well as its augmentations as …

Representation learning promises to unlock deep learning for the long tail of vision tasks
without expensive labelled datasets. Yet, the absence of a unified evaluation for general …

We develop an approach to learning visual representations that embraces multimodal data,
driven by a combination of intra-and inter-modal similarity preservation objectives. Unlike …