GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learning
CoRR(2024)
摘要
Deep neural networks often exhibit sub-optimal performance under covariate
and category shifts. Source-Free Domain Adaptation (SFDA) presents a promising
solution to this dilemma, yet most SFDA approaches are restricted to closed-set
scenarios. In this paper, we explore Source-Free Universal Domain Adaptation
(SF-UniDA) aiming to accurately classify "known" data belonging to common
categories and segregate them from target-private "unknown" data. We propose a
novel Global and Local Clustering (GLC) technique, which comprises an adaptive
one-vs-all global clustering algorithm to discern between target classes,
complemented by a local k-NN clustering strategy to mitigate negative transfer.
Despite the effectiveness, the inherent closed-set source architecture leads to
uniform treatment of "unknown" data, impeding the identification of distinct
"unknown" categories. To address this, we evolve GLC to GLC++, integrating a
contrastive affinity learning strategy. We examine the superiority of GLC and
GLC++ across multiple benchmarks and category shift scenarios. Remarkably, in
the most challenging open-partial-set scenarios, GLC and GLC++ surpass GATE by
16.7
category clustering accuracy of GLC by 4.3
Office-Home. Furthermore, the introduced contrastive learning strategy not only
enhances GLC but also significantly facilitates existing methodologies.
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