Large-scale data from real-world usually follow a long-tailed distribution (ie, a few majority
classes occupy plentiful training data, while most minority classes have few samples) …

The problem of class imbalanced data is that the generalization performance of the classifier
deteriorates due to the lack of data from minority classes. In this paper, we propose a novel …

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

Real-world data is often unbalanced and long-tailed, but deep models struggle to recognize
rare classes in the presence of frequent classes. To address unbalanced data, most studies …

Unlike the case when using a balanced training dataset, the per-class recall (ie, accuracy) of
neural networks trained with an imbalanced dataset are known to vary a lot from category to …

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 …

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

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 …

The long-tailed data distribution is prevalent in real world and it poses great challenge on
deep neural network training. In this paper, we propose Margin-aware Rectified …

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 …