OneRing: A Simple Method for Source-free Open-partial Domain Adaptation
This addresses domain adaptation with privacy constraints for machine learning applications, though it is incremental as it builds on existing open-partial domain adaptation methods.
The paper tackles source-free open-partial domain adaptation, where models adapt to target domains with category shifts without accessing source data due to privacy, and shows that their simple method outperforms existing approaches requiring source data, achieving gains of 2.5%, 7.2%, and 13% on standard benchmarks.
In this paper, we investigate Source-free Open-partial Domain Adaptation (SF-OPDA), which addresses the situation where there exist both domain and category shifts between source and target domains. Under the SF-OPDA setting, which aims to address data privacy concerns, the model cannot access source data anymore during target adaptation. We propose a novel training scheme to learn a (n+1)-way classifier to predict the n source classes and the unknown class, where samples of only known source categories are available for training. Furthermore, for target adaptation, we simply adopt a weighted entropy minimization to adapt the source pretrained model to the unlabeled target domain without source data. In experiments, we show our simple method surpasses current OPDA approaches which demand source data during adaptation. When augmented with a closed-set domain adaptation approach during target adaptation, our source-free method further outperforms the current state-of-the-art OPDA method by 2.5%, 7.2% and 13% on Office-31, Office-Home and VisDA respectively.