English

Generalized Categories Discovery for Long-tailed Recognition

Computer Vision and Pattern Recognition 2024-08-27 v2 Machine Learning

Abstract

Generalized Class Discovery (GCD) plays a pivotal role in discerning both known and unknown categories from unlabeled datasets by harnessing the insights derived from a labeled set comprising recognized classes. A significant limitation in prevailing GCD methods is their presumption of an equitably distributed category occurrence in unlabeled data. Contrary to this assumption, visual classes in natural environments typically exhibit a long-tailed distribution, with known or prevalent categories surfacing more frequently than their rarer counterparts. Our research endeavors to bridge this disconnect by focusing on the long-tailed Generalized Category Discovery (Long-tailed GCD) paradigm, which echoes the innate imbalances of real-world unlabeled datasets. In response to the unique challenges posed by Long-tailed GCD, we present a robust methodology anchored in two strategic regularizations: (i) a reweighting mechanism that bolsters the prominence of less-represented, tail-end categories, and (ii) a class prior constraint that aligns with the anticipated class distribution. Comprehensive experiments reveal that our proposed method surpasses previous state-of-the-art GCD methods by achieving an improvement of approximately 6 - 9% on ImageNet100 and competitive performance on CIFAR100.

Keywords

Cite

@article{arxiv.2401.05352,
  title  = {Generalized Categories Discovery for Long-tailed Recognition},
  author = {Ziyun Li and Christoph Meinel and Haojin Yang},
  journal= {arXiv preprint arXiv:2401.05352},
  year   = {2024}
}

Comments

ICCV 2023 out-of-distribution generalization in computer vision workshop paper

R2 v1 2026-06-28T14:13:29.295Z