LEAD: Learning Decomposition for Source-free Universal Domain Adaptation
CVPR 2024(2024)
摘要
Universal Domain Adaptation (UniDA) targets knowledge transfer in the
presence of both covariate and label shifts. Recently, Source-free Universal
Domain Adaptation (SF-UniDA) has emerged to achieve UniDA without access to
source data, which tends to be more practical due to data protection policies.
The main challenge lies in determining whether covariate-shifted samples belong
to target-private unknown categories. Existing methods tackle this either
through hand-crafted thresholding or by developing time-consuming iterative
clustering strategies. In this paper, we propose a new idea of LEArning
Decomposition (LEAD), which decouples features into source-known and -unknown
components to identify target-private data. Technically, LEAD initially
leverages the orthogonal decomposition analysis for feature decomposition.
Then, LEAD builds instance-level decision boundaries to adaptively identify
target-private data. Extensive experiments across various UniDA scenarios have
demonstrated the effectiveness and superiority of LEAD. Notably, in the OPDA
scenario on VisDA dataset, LEAD outperforms GLC by 3.5
reduces 75
is also appealing in that it is complementary to most existing methods. The
code is available at https://github.com/ispc-lab/LEAD.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要