Real-world data universally confronts a severe class-imbalance problem and exhibits a long-
tailed distribution, ie, most labels are associated with limited instances. The naïve models …

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 …

Real-world training data usually exhibits long-tailed distribution, where several majority
classes have a significantly larger number of samples than the remaining minority classes …

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 …

Real-world imagery is often characterized by a significant imbalance of the number of
images per class, leading to long-tailed distributions. An effective and simple approach to …

Deep neural networks have achieved great success on many visual recognition tasks.
However, training data with a long-tailed distribution dramatically degenerates the …

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) …

Recently, computer vision foundation models such as CLIP and ALI-GN, have shown
impressive generalization capabilities on various downstream tasks. But their abilities to …

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 …

Long-tailed visual recognition tasks pose great challenges for neural networks on how to
handle the imbalanced predictions between head (common) and tail (rare) classes, ie …