通过动态调整分类边界，显著提升难分类别准确率
Reducing Class-Wise Performance Disparity via Margin Regularization
- 基于类别特征方差动态调节分类边界
- 在7个数据集上平均提升难类别准确率1.8%以上
- 适用于预训练模型微调，适合关注公平性的场景
深度神经网络即使在类别平衡数据上训练，仍存在显著的类别间准确率差异，影响实际部署可靠性。本文提出一种理论驱动的分类正则化方法MR²，通过在logit和表示空间动态调整类别边界，缓解性能差距。理论分析揭示了类别特征方差对误差的影响，据此为难分类别设置更大边界，并惩罚过大的表示边界以增强类内紧凑性。在包括ImageNet在内的七个数据集及多种预训练主干（MAE、MoCov2、CLIP）上的实验表明，MR²不仅提升整体准确率，更显著改善难分类别表现，且不牺牲易分类别性能，有效降低类别间性能差异。代码已开源。
原文摘要 · Abstract (English)
Deep neural networks often exhibit substantial disparities in class-wise accuracy, even when trained on class-balanced data, posing concerns for reliable deployment. While prior efforts have explored empirical remedies, a theoretical understanding of such performance disparities in classification remains limited. In this work, we present Margin Regularization for Performance Disparity Reduction (MR$^2$), a theoretically principled regularization for classification by dynamically adjusting margins in both the logit and representation spaces. Our analysis establishes a margin-based, class-sensitive generalization bound that reveals how per-class feature variability contributes to error, motivating the use of larger margins for hard classes. Guided by this insight, MR$^2$ optimizes per-class logit margins proportional to feature spread and penalizes excessive representation margins to enhance intra-class compactness. Experiments on seven datasets, including ImageNet, and diverse pre-trained backbones (MAE, MoCov2, CLIP) demonstrate that MR$^2$ not only improves overall accuracy but also significantly boosts hard class performance without trading off easy classes, thus reducing performance disparity. Code is available at: https://github.com/BeierZhu/MR2
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。