{"ID":2858470,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.08836","arxiv_id":"2510.08836","title":"Long-Tailed Recognition via Information-Preservable Two-Stage Learning","abstract":"The imbalance (or long-tail) is the nature of many real-world data distributions, which often induces the undesirable bias of deep classification models toward frequent classes, resulting in poor performance for tail classes. In this paper, we propose a novel two-stage learning approach to mitigate such a majority-biased tendency while preserving valuable information within datasets. Specifically, the first stage proposes a new representation learning technique from the information theory perspective. This approach is theoretically equivalent to minimizing intra-class distance, yielding an effective and well-separated feature space. The second stage develops a novel sampling strategy that selects mathematically informative instances, able to rectify majority-biased decision boundaries without compromising a model's overall performance. As a result, our approach achieves the state-of-the-art performance across various long-tailed benchmark datasets, validated via extensive experiments. Our code is available at https://github.com/fudong03/BNS_IPDPP.","short_abstract":"The imbalance (or long-tail) is the nature of many real-world data distributions, which often induces the undesirable bias of deep classification models toward frequent classes, resulting in poor performance for tail classes. In this paper, we propose a novel two-stage learning approach to mitigate such a majority-bias...","url_abs":"https://arxiv.org/abs/2510.08836","url_pdf":"https://arxiv.org/pdf/2510.08836v1","authors":"[\"Fudong Lin\",\"Xu Yuan\"]","published":"2025-10-09T21:49:12Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false,"code_links":[{"ID":608546,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2858470,"paper_url":"https://arxiv.org/abs/2510.08836","paper_title":"Long-Tailed Recognition via Information-Preservable Two-Stage Learning","repo_url":"https://github.com/fudong03/BNS_IPDPP","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}