Although deep learning algorithms have achieved significant progress in a variety of
domains, they require costly annotations on huge datasets. Self-supervised learning (SSL) …

We present DocFormer-a multi-modal transformer based architecture for the task of Visual
Document Understanding (VDU). VDU is a challenging problem which aims to understand …

We propose DocFormerv2, a multi-modal transformer for Visual Document Understanding
(VDU). The VDU domain entails understanding documents (beyond mere OCR predictions) …

Whole slide image (WSI) classification often relies on deep weakly supervised multiple
instance learning (MIL) methods to handle gigapixel resolution images and slide-level …

By leveraging contrastive learning, clustering, and other pretext tasks, unsupervised
methods for learning image representations have reached impressive results on standard …

Recently, self-supervised learning (SSL) has achieved tremendous success in learning
image representation. Despite the empirical success, most self-supervised learning methods …

Instance-wise contrastive learning (Instance-CL), which learns to map similar instances
closer and different instances farther apart in the embedding space, has achieved …

Self-supervised learning (SSL) is typically evaluated using a single metric (linear probing on
ImageNet), which neither provides insight into tradeoffs between models nor highlights how …

One unexpected technique that emerged in recent years consists in training a Deep Network
(DN) with a Self-Supervised Learning (SSL) method, and using this network on downstream …

Self-supervised learning (SSL) aims to learn intrinsic features without labels. Despite the
diverse architectures of SSL methods, the projection head always plays an important role in …