TY  - JOUR
AU  - Shiqi Yang
AU  - Yaxing Wang
AU  - Luis Herranz
AU  - Shangling Jui
AU  - Joost Van de Weijer
PY  - 2023//
TI  - Casting a BAIT for offline and online source-free domain adaptation
T2  - CVIU
JO  - Computer Vision and Image Understanding
SP  - 103747
VL  - 234
N2  - We address the source-free domain adaptation (SFDA) problem, where only the source model is available during adaptation to the target domain. We consider two settings: the offline setting where all target data can be visited multiple times (epochs) to arrive at a prediction for each target sample, and the online setting where the target data needs to be directly classified upon arrival. Inspired by diverse classifier based domain adaptation methods, in this paper we introduce a second classifier, but with another classifier head fixed. When adapting to the target domain, the additional classifier initialized from source classifier is expected to find misclassified features. Next, when updating the feature extractor, those features will be pushed towards the right side of the source decision boundary, thus achieving source-free domain adaptation. Experimental results show that the proposed method achieves competitive results for offline SFDA on several benchmark datasets compared with existing DA and SFDA methods, and our method surpasses by a large margin other SFDA methods under online source-free domain adaptation setting.
UR  - https://www.sciencedirect.com/science/article/abs/pii/S1077314223001273
N1  - LAMP; MACO
ID  - Shiqi Yang2023
ER  -