提升无监督域适应中各类别的公平性，让模型不再偏爱容易分类的类别。
Learning Fair Domain Adaptation with Virtual Label Distribution
- 通过自适应加权增强难分类类别的影响
- 引入基于KL散度的再平衡策略优化决策边界
- 可直接嵌入现有方法，显著改善最差类别性能
无监督域适应（UDA）旨在缓解训练与测试数据分布不一致导致的性能下降。尽管整体准确率已有显著提升，但多数方法忽视了类别间的性能差异——我们称之为类别公平性问题。实证分析表明，现有UDA分类器倾向于偏好某些易分类类别，而忽略困难类别。为此，本文提出虚拟标签分布感知学习（VILL），一种简单有效的框架，在保持高整体准确率的同时提升最差类别表现。VILL的核心是自适应重加权策略，放大难分类类别的影响；同时引入基于KL散度的再平衡机制，显式调整决策边界以增强类别公平性。在常用数据集上的实验表明，VILL可作为即插即用模块无缝集成到现有UDA方法中，显著提升类别公平性。
原文摘要 · Abstract (English)
Unsupervised Domain Adaptation (UDA) aims to mitigate performance degradation when training and testing data are sampled from different distributions. While significant progress has been made in enhancing overall accuracy, most existing methods overlook performance disparities across categories-an issue we refer to as category fairness. Our empirical analysis reveals that UDA classifiers tend to favor certain easy categories while neglecting difficult ones. To address this, we propose Virtual Label-distribution-aware Learning (VILL), a simple yet effective framework designed to improve worst-case performance while preserving high overall accuracy. The core of VILL is an adaptive re-weighting strategy that amplifies the influence of hard-to-classify categories. Furthermore, we introduce a KL-divergence-based re-balancing strategy, which explicitly adjusts decision boundaries to enhance category fairness. Experiments on commonly used datasets demonstrate that VILL can be seamlessly integrated as a plug-and-play module into existing UDA methods, significantly improving category fairness.
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。