解决数据长尾问题，让模型不再偏爱常见类别
Long-Tailed Recognition via Information-Preservable Two-Stage Learning
- 从信息论出发设计特征学习方法，实现类内紧凑、类间分离
- 提出数学上可解释的采样策略，提升尾部类别识别性能
- 适用于各类长尾数据集，特别适合对公平性要求高的场景
现实世界数据分布普遍存在类别不平衡问题，导致深度分类模型对高频类别产生偏差，影响尾部类别的表现。本文提出一种信息保全的两阶段学习方法，有效缓解这一多数类偏向问题。第一阶段基于信息论提出新的表征学习技术，理论上等价于最小化类内距离，构建出高效且分离良好的特征空间。第二阶段设计了一种数学上可解释的采样策略，选择最具信息量的样本，修正多数类主导的决策边界，同时保持模型整体性能。在多个长尾基准数据集上的大量实验验证了该方法达到当前最优效果。代码已公开于https://github.com/fudong03/BNS_IPDPP。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。