Back to Search Start Over

Source-Free Domain Adaptation via Distribution Estimation

Authors :
Ding, Ning
Xu, Yixing
Tang, Yehui
Xu, Chao
Wang, Yunhe
Tao, Dacheng
Source :
CVPR2022
Publication Year :
2022

Abstract

Domain Adaptation aims to transfer the knowledge learned from a labeled source domain to an unlabeled target domain whose data distributions are different. However, the training data in source domain required by most of the existing methods is usually unavailable in real-world applications due to privacy preserving policies. Recently, Source-Free Domain Adaptation (SFDA) has drawn much attention, which tries to tackle domain adaptation problem without using source data. In this work, we propose a novel framework called SFDA-DE to address SFDA task via source Distribution Estimation. Firstly, we produce robust pseudo-labels for target data with spherical k-means clustering, whose initial class centers are the weight vectors (anchors) learned by the classifier of pretrained model. Furthermore, we propose to estimate the class-conditioned feature distribution of source domain by exploiting target data and corresponding anchors. Finally, we sample surrogate features from the estimated distribution, which are then utilized to align two domains by minimizing a contrastive adaptation loss function. Extensive experiments show that the proposed method achieves state-of-the-art performance on multiple DA benchmarks, and even outperforms traditional DA methods which require plenty of source data.

Details

Database :
arXiv
Journal :
CVPR2022
Publication Type :
Report
Accession number :
edsarx.2204.11257
Document Type :
Working Paper