Unsupervised Domain Adaptation for Segmentation with Black-box Source Model

Xiaofeng Liu, Chaehwa Yoo, Fangxu Xing, C. C.Jay Kuo, Georges El Fakhri, Je Won Kang, Jonghye Woo

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

8 Scopus citations

Abstract

Unsupervised domain adaptation (UDA) has been widely used to transfer knowledge from a labeled source domain to an unlabeled target domain to counter the difficulty of labeling in a new domain. The training of conventional solutions usually relies on the existence of both source and target domain data. However, privacy of the large-scale and well-labeled data in the source domain and trained model parameters can become the major concern of cross center/domain collaborations. In this work, to address this, we propose a practical solution to UDA for segmentation with a black-box segmentation model trained in the source domain only, rather than original source data or a white-box source model. Specifically, we resort to a knowledge distillation scheme with exponential mixup decay (EMD) to gradually learn target-specific representations. In addition, unsupervised entropy minimization is further applied to regularization of the target domain confidence. We evaluated our framework on the BraTS 2018 database, achieving performance on par with white-box source model adaptation approaches.

Original languageEnglish
Title of host publicationMedical Imaging 2022
Subtitle of host publicationImage Processing
EditorsOlivier Colliot, Ivana Isgum, Bennett A. Landman, Murray H. Loew
PublisherSPIE
ISBN (Electronic)9781510649392
DOIs
StatePublished - 2022
EventMedical Imaging 2022: Image Processing - Virtual, Online
Duration: 21 Mar 202127 Mar 2021

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume12032
ISSN (Print)1605-7422

Conference

ConferenceMedical Imaging 2022: Image Processing
CityVirtual, Online
Period21/03/2127/03/21

Bibliographical note

Funding Information:
This work is partially supported by NIH R01DC018511 and P41EB022544.

Publisher Copyright:
© 2022 SPIE.

Keywords

  • Black-box source model
  • Brain MR image segmentation
  • Unsupervised domain adaptation

Fingerprint

Dive into the research topics of 'Unsupervised Domain Adaptation for Segmentation with Black-box Source Model'. Together they form a unique fingerprint.

Cite this