Long-tailed recognition with imbalanced class distribution naturally emerges in practical
machine learning applications. Existing methods such as data reweighing, resampling, and …

Real-world data often exhibits long tail distributions with heavy class imbalance, where the
majority classes can dominate the training process and alter the decision boundaries of the …

Supervised Contrastive Loss (SCL) is popular in visual representation learning. Given an
anchor image, SCL pulls two types of positive samples, ie, its augmentation and other …

Real-world data often follows a long-tailed distribution, where a few head classes occupy
most of the data and a large number of tail classes only contain very limited samples. In …

It's widely acknowledged that deep learning models with flatter minima in its loss landscape
tend to generalize better. However, such property is under-explored in deep long-tailed …

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 …

The problem of long-tailed recognition, where the number of examples per class is highly
unbalanced, is considered. It is hypothesized that the well known tendency of standard …

Thanks to the advances in deep learning-based computer vision, image classification has
shown great achievements. However, it has faced a heavy class imbalance issue which is …

Most deep learning models are elaborately designed for balanced datasets, and thus they
inevitably suffer performance degradation in practical long-tailed recognition tasks …

Long-tailed image recognition presents massive challenges to deep learning systems since
the imbalance between majority (head) classes and minority (tail) classes severely skews …