Recently, self-supervised learning has attracted great attention, since it only requires
unlabeled data for model training. Contrastive learning is one popular method for self …

In generative modeling, numerous successful approaches leverage a low-dimensional
latent space, eg, Stable Diffusion models the latent space induced by an encoder and …

The proliferation of pretrained models, as a result of advancements in pretraining
techniques, has led to the emergence of a vast zoo of publicly available models. Effectively …

Contrastive learning has shown outstanding performances in both supervised and
unsupervised learning, and has recently been introduced to solve weakly supervised …

In this paper, we provide a comprehensive toolbox for understanding and enhancing self-
supervised learning (SSL) methods through the lens of matrix information theory …

Contrastive learning is a powerful self-supervised learning method, but we have a limited
theoretical understanding of how it works and why it works. In this paper, we prove that …

Self-Supervised Learning (SSL) is a paradigm that leverages unlabeled data for model
training. Empirical studies show that SSL can achieve promising performance in distribution …

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 …

The maximum entropy encoding framework provides a unified perspective for many non-
contrastive learning methods like SimSiam, Barlow Twins, and MEC. Inspired by this …

Visualization methods based on the nearest neighbor graph, such as t-SNE or UMAP, are
widely used for visualizing high-dimensional data. Yet, these approaches only produce …