Tight Source Domain Match for Partial Domain Adaptation Based on Maximum Density

Zi Ao Ni, Zixian Su, Xi Yang*, Qiufeng Wang, Kaizhu Huang

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review


Unsupervised domain adaptation (UDA) aims at transferring knowledge between a well-labelled 'source domain' and an unlabelled 'target domain' by decreasing distribution discrepancy. In real scenario, partial domain adaptation (PDA), where target domain only includes part of the classes of source domain, is adopted as fully-shared label space is often unavailable. Non-identical label spaces across domains lead to performance degradation due to source-unique classes being mis-matched to the target domain, i.e. negative transfer of the target domain. Although existing PDA approaches have produced promising results, they still confront with negative transfer problem without rigorous generalization bounds. In our work, a novel PDA model has been proposed based on margin disparity and maximum source intra-class density divergence (MDSD). It matches the feature distributions with shared labels and congregates source samples in the source with affirmative labels. Removing maximum target density with pseudo labels, it effectively avoids over-fitting and accelerates learning speed. In addition, we construct a new garbage classification dataset, which is comprised of source domain - Product (Pr) and target domain - Garbage (Ga) for PDA validation. Experiments show that our proposed unsupervised partial domain adaptation method has a good performance on Office-31, Office-Home and Pr-Ga datasets.

Original languageEnglish
Article number012032
JournalJournal of Physics: Conference Series
Issue number1
Publication statusPublished - 1 Jun 2022
Event2022 6th International Conference on Machine Vision and Information Technology, CMVIT 2022 - Virtual, Online
Duration: 25 Feb 2022 → …


Dive into the research topics of 'Tight Source Domain Match for Partial Domain Adaptation Based on Maximum Density'. Together they form a unique fingerprint.

Cite this