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) …

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 …

Deep models trained on long-tailed datasets exhibit unsatisfactory performance on tail
classes. Existing methods usually modify the classification loss to increase the learning …

We address the overlooked unbiasedness in existing long-tailed classification methods: we
find that their overall improvement is mostly attributed to the biased preference of" tail" over" …

Long-tailed recognition with imbalanced class distribution naturally emerges in practical
machine learning applications. Existing methods such as data reweighing, resampling, and …

In this work, we introduce a novel strategy for long-tail recognition that addresses the tail
classes' few-shot problem via training-free knowledge transfer. Our objective is to transfer …

Long-tailed distribution of remote sensing data generally limits the object recognition
performance of deep neural networks. We notice that too many samples from head class will …

Decoupling representation learning and classifier learning has been shown to be effective in
classification with long-tailed data. There are two main ingredients in constructing a …

Class-incremental learning (CIL) has emerged as a means to learn new classes
incrementally without catastrophic forgetting of previous classes. Recently, CIL has …

Abstract Machine learning models fail to perform well on real-world applications when 1) the
category distribution P (Y) of the training dataset suffers from long-tailed distribution and 2) …