The downstream accuracy of self-supervised methods is tightly linked to the proxy task
solved during training and the quality of the gradients extracted from it. Richer and more …

Most self-supervised methods for representation learning leverage a cross-view consistency
objective ie, they maximize the representation similarity of a given image's augmented …

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 …

State-of-the-art frameworks in self-supervised learning have recently shown that fully
utilizing transformer-based models can lead to performance boost compared to conventional …

In recent years, discriminative self-supervised methods have made significant strides in
advancing various visual tasks. The central idea of learning a data encoder that is robust to …

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

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

Self-supervised visual representation methods are closing the gap with supervised learning
performance. These methods rely on maximizing the similarity between embeddings of …

The resurgence of unsupervised learning can be attributed to the remarkable progress of
self-supervised learning, which includes generative (G) and discriminative (D) models. In …

The rapid advancement in self-supervised learning (SSL) has highlighted its potential to
leverage unlabeled data for learning powerful visual representations. However, existing SSL …