Selective Partial Domain Adaptation

Pengxin Guo (Southern University of Science and Technology),* Jinjing Zhu (Southern University of Science and Technology), Yu Zhang (Southern University of Science and Technology)
The 33rd British Machine Vision Conference


Partial Domain Adaptation (PDA), which assumes that the label space of the target domain is a subset of that in the source domain, has attracted much attention in recent years. Due to the difference in the label space of these two domains, it is hard to directly align these two domains in PDA. To solve this problem, we propose a Selective Partial Domain Adaptation (SPDA) method, which selects useful data for the adaptation to the target domain. Specifically, we firstly design a Maximum of Cosine (MoC) similarity function customized for PDA to select useful data in the source domain to decrease the domain discrepancy. In the MoC similarity function, for each target sample, we select the source sample with the maximal cosine similarity for adaptation. Moreover, a selective training method is designed to add useful target data into the source domain. In detail, the selective training method firstly assigns pseudo-labels to target samples with the self-training strategy and then adds target samples with high confidence in terms of pseudo-labels to the source domain. Based on these two selection operations, the proposed SPDA method can select useful data for domain adaptation. Experiments on several datasets demonstrate the effectiveness of the proposed SPDA method.



author    = {Pengxin Guo and Jinjing Zhu and Yu Zhang},
title     = {Selective Partial Domain Adaptation},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year      = {2022},
url       = {}

Copyright © 2022 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection