Deep learning is driving recent advances behind many everyday technologies, including
speech and image recognition, natural language processing and autonomous driving. It is …

Temporal action segmentation (TAS) in videos aims at densely identifying video frames in
minutes-long videos with multiple action classes. As a long-range video understanding task …

Deep long-tailed learning, one of the most challenging problems in visual recognition, aims
to train well-performing deep models from a large number of images that follow a long-tailed …

The ability to learn new concepts continually is necessary in this ever-changing world.
However, deep neural networks suffer from catastrophic forgetting when learning new …

Real-world data typically follow a long-tailed distribution, where a few majority categories
occupy most of the data while most minority categories contain a limited number of samples …

We address the problem of class incremental learning, which is a core step towards
achieving adaptive vision intelligence. In particular, we consider the task setting of …

Building instance segmentation models that are data-efficient and can handle rare object
categories is an important challenge in computer vision. Leveraging data augmentations is a …

In this paper, we propose Parametric Contrastive Learning (PaCo) to tackle long-tailed
recognition. Based on theoretical analysis, we observe supervised contrastive loss tends to …

Despite the visually-pleasing results achieved, the massive computational cost has been a
long-standing flaw for diffusion probabilistic models (DPMs), which, in turn, greatly limits …

Recent self-supervised methods for image representation learning are based on maximizing
the agreement between embedding vectors from different views of the same image. A trivial …