The real-world data tends to be heavily imbalanced and severely skew the data-driven deep
neural networks, which makes Long-Tailed Recognition (LTR) a massive challenging task …

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

Abstract Deep Neural Networks (DNNs) are rather restrictive in long-tailed data, since they
commonly exhibit an under-representation for minority classes. Various remedies have been …

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 recent years, visual recognition on challenging long-tailed distributions, where classes
often exhibit extremely imbalanced frequencies, has made great progress mostly based on …

Deep learning has achieved remarkable progress for visual recognition on large-scale
balanced datasets but still performs poorly on real-world long-tailed data. Previous methods …

Our work focuses on tackling the challenging but natural visual recognition task of long-
tailed data distribution (ie, a few classes occupy most of the data, while most classes have …

Deep learning has achieved remarkable success in recent years; however, deep learning
methods face significant challenges on long-tailed datasets, which are prevalent in real …

The networks trained on the long-tailed dataset vary remarkably, despite the same training
settings, which shows the great uncertainty in long-tailed learning. To alleviate the …

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 …