解决目标域表征维度坍塌，提升极端场景下的通用领域适应性能
Tackling Dimensional Collapse toward Comprehensive Universal Domain Adaptation
- 在无监督领域适应中利用自监督学习技术恢复目标域表征结构
- 在不同共享类别比例下均超越现有方法，实现新最优结果
- 适合研究通用领域适应、表征学习与跨域迁移的学者
通用领域适应（UniDA）处理目标域类别与源域任意不同的无监督域适应问题，仅存在共享子集。常用方法部分域匹配（PDM）仅对齐共享类别，但在源类大量缺失于目标域的极端情况下表现不佳，甚至低于仅在源数据上训练的最简单基线。本文发现其失败根源在于目标表示的维度坍塌（DC）。为缓解此问题，我们提出在未标注目标数据上应用自监督学习中的去坍塌技术，以保留表征的内在结构。实验验证，自监督学习能持续提升PDM性能，并在涵盖不同共享类别比例的更广泛基准上取得新最佳结果，推动真正全面的通用领域适应发展。
原文摘要 · Abstract (English)
Universal Domain Adaptation (UniDA) addresses unsupervised domain adaptation where target classes may differ arbitrarily from source ones, except for a shared subset. A widely used approach, partial domain matching (PDM), aligns only shared classes but struggles in extreme cases where many source classes are absent in the target domain, underperforming the most naive baseline that trains on only source data. In this work, we identify that the failure of PDM for extreme UniDA stems from dimensional collapse (DC) in target representations. To address target DC, we propose to use the de-collapse techniques in self-supervised learning on the unlabeled target data to preserve the intrinsic structure of the learned representations. Our experimental results confirm that SSL consistently advances PDM and delivers new state-of-the-art results across a broader benchmark of UniDA scenarios with different portions of shared classes, representing a crucial step toward truly comprehensive UniDA. Project page: https://dc-unida.github.io/
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。