Learning the distribution of a continuous or categorical response variable y given its
covariates x is a fundamental problem in statistics and machine learning. Deep neural …

Self-supervised representation learning has made significant leaps fueled by progress in
contrastive learning, which seeks to learn transformations that embed positive input pairs …

Since the introduction of deep learning, a wide scope of representation properties, such as
decorrelation, whitening, disentanglement, rank, isotropy, and mutual information, have …

Multi-label image classification is a prediction task that aims to identify more than one label
from a given image. This paper considers the semantic consistency of the latent space …

Self-supervised learning has achieved a great success in the representation learning of
visual and textual data. However, the current methods are mainly validated on the well …

Diffusion models are acclaimed for generating high-quality and diverse images. However,
their performance notably degrades when trained on data with a long-tailed distribution. For …

As one of the fundamental video tasks in computer vision, Open-Vocabulary Action
Recognition (OVAR) recently gains increasing attention, with the development of vision …

Our work reveals a structured shortcoming of the existing mainstream self-supervised
learning methods. Whereas self-supervised learning frameworks usually take the prevailing …

We study the problem of designing hard negative sampling distributions for unsupervised
contrastive representation learning. We propose and analyze a novel min-max framework …

Despite the remarkable success of deep learning in medical imaging analysis, medical
image segmentation remains challenging due to the scarcity of high-quality labeled images …