Deep supervised learning algorithms typically require a large volume of labeled data to
achieve satisfactory performance. However, the process of collecting and labeling such data …

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 propose DiffCSE, an unsupervised contrastive learning framework for learning sentence
embeddings. DiffCSE learns sentence embeddings that are sensitive to the difference …

Abstract Self-Supervised Learning (SSL) surmises that inputs and pairwise positive
relationships are enough to learn meaningful representations. Although SSL has recently …

We introduce a conceptually simple yet effective model for self-supervised representation
learning with graph data. It follows the previous methods that generate two views of an input …

Abstract Visual Transformers (VTs) are emerging as an architectural paradigm alternative to
Convolutional networks (CNNs). Differently from CNNs, VTs can capture global relations …

Abstract Joint-Embedding Self Supervised Learning (JE-SSL) has seen a rapid
development, with the emergence of many method variations but only few principled …

Recent self-supervised contrastive learning methods greatly benefit from the Siamese
structure that aims at minimizing distances between positive pairs. For high performance …

In this paper, we address the problem of generalized category discovery (GCD), ie, given a
set of images where part of them are labelled and the rest are not, the task is to automatically …

Self-supervised visual representation learning aims to learn useful representations without
relying on human annotations. Joint embedding approach bases on maximizing the …