Saved in:
Bibliographic Details
Main Authors: Lin, Fudong, Yuan, Xu
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.08836
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914085756469248
author Lin, Fudong
Yuan, Xu
author_facet Lin, Fudong
Yuan, Xu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_08836
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Long-Tailed Recognition via Information-Preservable Two-Stage Learning
Lin, Fudong
Yuan, Xu
Machine Learning
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.
title Long-Tailed Recognition via Information-Preservable Two-Stage Learning
topic Machine Learning
url https://arxiv.org/abs/2510.08836