Deep neural networks usually perform poorly when the training dataset suffers from extreme
class imbalance. Recent studies found that directly training with out-of-distribution data (ie …

Real-world datasets are often highly class-imbalanced, which can adversely impact the
performance of deep learning models. The majority of research on training neural networks …

In most real-world scenarios, labeled training datasets are highly class-imbalanced, where
deep neural networks suffer from generalizing to a balanced testing criterion. In this paper …

Real-world data often exhibits long-tailed distributions with heavy class imbalance, posing
great challenges for deep recognition models. We identify a persisting dilemma on the value …

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

Neural networks trained with class-imbalanced data are known to perform poorly on minor
classes of scarce training data. Several recent works attribute this to over-fitting to minor …

A well-trained deep neural network on balanced datasets usually exhibits the Neural
Collapse (NC) phenomenon, which is an informative indicator of the model achieving good …

Real-world datasets exhibit imbalances of varying types and degrees. Several techniques
based on re-weighting and margin adjustment of loss are often used to enhance the …

Although deep neural networks achieve tremendous success on various classification tasks,
the generalization ability drops sheer when training datasets exhibit long-tailed distributions …

Real-world data often follow a long-tailed distribution as the frequency of each class is
typically different. For example, a dataset can have a large number of under-represented …