SoFA: Source-data-free Feature Alignment for Unsupervised Domain Adaptation

Hao-Wei Yeh, Baoyao Yang, Pong C. Yuen, Tatsuya Harada

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

47 Citations (Scopus)

Abstract

Applying a trained model on a new scenario may suffer from domain shift. Unsupervised domain adaptation (UDA) has been proven to be an effective approach to solve the problem of domain shift by leveraging both data from the scenario that the model was trained on (source) and the new scenario (target). Although the source data are available for training the source model, there is no guarantee that the source data will still be available when applying UDA in the future due to emerging regulations on privacy of data. This results in the in-applicability of most existing UDA methods in the absence of source data. This paper proposes a source-data-free feature alignment (SoFA) method to address this problem by only using the trained source model and unlabeled target data. The source model is used to predict the labels for target data, and we model the generation process from predicted classes to input data to infer the latent features for alignment. Specifically, a mixture of Gaussian distributions is induced from the predicted classes as the reference distribution. The encoded target features are then aligned to the reference distribution via variational inference to extract class semantics without accessing source data. Relationship of the proposed method and the theory of domain adaptation is provided to verify the performance. Experimental results show the proposed method achieves higher or comparable accuracy compared to the existing methods in several cross-dataset classification tasks. Ablation studies are also conducted to confirm the importance of latent feature alignment to adaptation performance.
Original languageEnglish
Title of host publicationProceedings - 2021 IEEE Winter Conference on Applications of Computer Vision, WACV 2021
PublisherIEEE
Pages474-483
Number of pages10
ISBN (Print)9780738142661
DOIs
Publication statusPublished - Jan 2021
Event2021 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2021 - Online
Duration: 5 Jan 20219 Jan 2021
https://wacv2021.thecvf.com/home
https://wacv2021.thecvf.com/program

Publication series

NameProceedings - IEEE Workshop on Applications of Computer Vision (WACV)
PublisherIEEE

Conference

Conference2021 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2021
CityOnline
Period5/01/219/01/21
Internet address

Fingerprint

Dive into the research topics of 'SoFA: Source-data-free Feature Alignment for Unsupervised Domain Adaptation'. Together they form a unique fingerprint.

Cite this