Many real-world recognition problems are characterized by long-tailed label distributions.
These distributions make representation learning highly challenging due to limited …

Recently, multi-expert methods have led to significant improvements in long-tail recognition
(LTR). We summarize two aspects that need further enhancement to contribute to LTR …

The long-tail distribution of the visual world poses great challenges for deep learning based
classification models on how to handle the class imbalance problem. Existing solutions …

Deep learning algorithms face great challenges with long-tailed data distribution which,
however, is quite a common case in real-world scenarios. Previous methods tackle the …

Deep neural networks may perform poorly when training datasets are heavily class-
imbalanced. Recently, two-stage methods decouple representation learning and classifier …

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 this paper, our goal is to design a simple learning paradigm for long-tail visual
recognition, which not only improves the robustness of the feature extractor but also …

Class imbalance problems frequently occur in real-world tasks, and conventional deep
learning algorithms are well known for performance degradation on imbalanced training …

The visual world naturally exhibits a long-tailed distribution of open classes, which poses
great challenges to modern visual systems. Existing approaches either perform class re …

Deep neural networks excel in visual recognition tasks, but their success hinges on access
to balanced datasets. Yet, real-world datasets often exhibit a long-tailed distribution …