Long-tail learning has received significant attention in recent years due to the challenge it
poses with extremely imbalanced datasets. In these datasets, only a few classes (known as …

In the quest for unveiling novel categories at test time, we confront the inherent limitations of
traditional supervised recognition models that are restricted by a predefined category set …

Representation learning for images has been advanced by recent progress in more complex
neural models such as the Vision Transformers and new learning theories such as the …

In scenarios with long-tailed distributions, the model's ability to identify tail classes is limited
due to the under-representation of tail samples. Class rebalancing, information …

The long-tailed distribution data poses many challenges for machine learning because the
tail classes are extremely scarce. Long-tailed data augmentation is a powerful technique for …

Real-world tasks are universally associated with training samples that exhibit a long-tailed
class distribution, and traditional deep learning models are not suitable for fitting this …

Deep neural networks are vulnerable to adversarial attacks leading to erroneous outputs.
Adversarial training has been recognized as one of the most effective methods to counter …

The fine-tuning paradigm in addressing long-tail learning tasks has sparked significant
interest since the emergence of foundation models. Nonetheless, how fine-tuning impacts …

The real-world data distribution is essentially long-tailed, which poses a significant
challenge to the deep model. Classification models minimizing cross-entropy loss struggle …

This paper proposes a new pipeline for long-tail (LT) recognition. Instead of re-weighting or
re-sampling, we utilize the long-tailed dataset itself to generate a balanced proxy that can be …