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 …

Graph learning is a popular approach for perfor ming machine learning on graph-structured
data. It has revolutionized the machine learning ability to model graph data to address …

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 …

Despite the success of the deep neural networks, it remains challenging to effectively build a
system for long-tail visual recognition tasks. To address this problem, we first investigate the …

Semi-supervised learning on class-imbalanced data, although a realistic problem, has been
under studied. While existing semi-supervised learning (SSL) methods are known to perform …

Learning discriminative image representations plays a vital role in long-tailed image
classification because it can ease the classifier learning in imbalanced cases. Given the …

In the real open world, data tends to follow long-tailed class distributions, motivating the well-
studied long-tailed recognition (LTR) problem. Naive training produces models that are …

Traditional federated optimization methods perform poorly with heterogeneous data (ie,
accuracy reduction), especially for highly skewed data. In this paper, we investigate the label …

In the real world, large-scale datasets for visual recognition typically exhibit a long-tailed
distribution, where only a few classes contain adequate samples but the others have (much) …

The heavy reliance on data is one of the major reasons that currently limit the development
of deep learning. Data quality directly dominates the effect of deep learning models, and the …