Current deep neural networks (DNNs) can easily overfit to biased training data with
corrupted labels or class imbalance. Sample re-weighting strategy is commonly used to …

Existing self-supervised learning (SSL) methods are mostly applied for training
representation models from artificially balanced datasets (eg, ImageNet). It is unclear how …

The coronavirus disease (COVID-19) is rapidly spreading all over the world, and has
infected more than 1,436,000 people in more than 200 countries and territories as of April 9 …

We introduce here a large tracking database that offers an unprecedentedly wide coverage
of common moving objects in the wild, called GOT-10k. Specifically, GOT-10k is built upon …

Real-world data often follow a long-tailed distribution as the frequency of each class is
typically different. For example, a dataset can have a large number of under-represented …

We present a new loss function called Distribution-Balanced Loss for the multi-label
recognition problems that exhibit long-tailed class distributions. Compared to conventional …

We study why overparameterization—increasing model size well beyond the point of zero
training error—can hurt test error on minority groups despite improving average test error …

Federated learning (FL) is a promising approach for training decentralized data located on
local client devices while improving efficiency and privacy. However, the distribution and …

One-stage long-tailed recognition methods improve the overall performance in a" seesaw"
manner, ie, either sacrifice the head's accuracy for better tail classification or elevate the …

Background Chest x-rays are widely used in clinical practice; however, interpretation can be
hindered by human error and a lack of experienced thoracic radiologists. Deep learning has …