PLPP: A Pseudo Labeling Post-Processing Strategy for Unsupervised Domain Adaptation

Tomer Bar Natan; Hayit Greenspan; Jacob Goldberger

doi:10.1109/isbi53787.2023.10230628

PLPP: A Pseudo Labeling Post-Processing Strategy for Unsupervised Domain Adaptation

Tomer Bar Natan, Hayit Greenspan, Jacob Goldberger

Bar-Ilan University - The Alexander Kofkin Faculty of Engineering

Tel Aviv University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

A well known problem in medical imaging is the ability to use an existing model learned on source data, in a new site. This is known as the domain shift problem. We propose a pseudo labels procedure, which was originally introduced for semi-supervised learning, that is suitable for unsupervised domain adaptation (UDA). We iteratively improve the pseudo labels of the target domain data only using the current pseudo labels without involving the labeled source domain data. We applied our method to several medical MRI image segmentation tasks. We show that, by combining our approach as a post-processing step in standard UDA algorithms, we consistently and significantly improve the segmentation results on test images from the target site.

Original language	English
Title of host publication	2023 IEEE International Symposium on Biomedical Imaging, ISBI 2023
Publisher	IEEE Computer Society
ISBN (Electronic)	9781665473583
DOIs	https://doi.org/10.1109/isbi53787.2023.10230628
State	Published - 2023
Event	20th IEEE International Symposium on Biomedical Imaging, ISBI 2023 - Cartagena, Colombia Duration: 18 Apr 2023 → 21 Apr 2023

Publication series

Name	Proceedings - International Symposium on Biomedical Imaging
Volume	2023-April
ISSN (Print)	1945-7928
ISSN (Electronic)	1945-8452

Conference

Conference	20th IEEE International Symposium on Biomedical Imaging, ISBI 2023
Country/Territory	Colombia
City	Cartagena
Period	18/04/23 → 21/04/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Funding

This research was supported by the Ministry of Science & Technology, Israel.

Funders	Funder number
Ministry of science and technology, Israel

Keywords

pseudo labels
site adaptation
transfer learning
unsupervised domain adaptation

Access to Document

10.1109/isbi53787.2023.10230628

Cite this

@inproceedings{eadd9d1ccdf940ff977799c4834162da,

title = "PLPP: A Pseudo Labeling Post-Processing Strategy for Unsupervised Domain Adaptation",

abstract = "A well known problem in medical imaging is the ability to use an existing model learned on source data, in a new site. This is known as the domain shift problem. We propose a pseudo labels procedure, which was originally introduced for semi-supervised learning, that is suitable for unsupervised domain adaptation (UDA). We iteratively improve the pseudo labels of the target domain data only using the current pseudo labels without involving the labeled source domain data. We applied our method to several medical MRI image segmentation tasks. We show that, by combining our approach as a post-processing step in standard UDA algorithms, we consistently and significantly improve the segmentation results on test images from the target site.",

keywords = "pseudo labels, site adaptation, transfer learning, unsupervised domain adaptation",

author = "Natan, {Tomer Bar} and Hayit Greenspan and Jacob Goldberger",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 20th IEEE International Symposium on Biomedical Imaging, ISBI 2023 ; Conference date: 18-04-2023 Through 21-04-2023",

year = "2023",

doi = "10.1109/isbi53787.2023.10230628",

language = "אנגלית",

series = "Proceedings - International Symposium on Biomedical Imaging",

publisher = "IEEE Computer Society",

booktitle = "2023 IEEE International Symposium on Biomedical Imaging, ISBI 2023",

address = "ארצות הברית",

}

Natan, TB, Greenspan, H & Goldberger, J 2023, PLPP: A Pseudo Labeling Post-Processing Strategy for Unsupervised Domain Adaptation. in 2023 IEEE International Symposium on Biomedical Imaging, ISBI 2023. Proceedings - International Symposium on Biomedical Imaging, vol. 2023-April, IEEE Computer Society, 20th IEEE International Symposium on Biomedical Imaging, ISBI 2023, Cartagena, Colombia, 18/04/23. https://doi.org/10.1109/isbi53787.2023.10230628

PLPP: A Pseudo Labeling Post-Processing Strategy for Unsupervised Domain Adaptation. / Natan, Tomer Bar; Greenspan, Hayit; Goldberger, Jacob.
2023 IEEE International Symposium on Biomedical Imaging, ISBI 2023. IEEE Computer Society, 2023. (Proceedings - International Symposium on Biomedical Imaging; Vol. 2023-April).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - PLPP

T2 - 20th IEEE International Symposium on Biomedical Imaging, ISBI 2023

AU - Natan, Tomer Bar

AU - Greenspan, Hayit

AU - Goldberger, Jacob

PY - 2023

Y1 - 2023

N2 - A well known problem in medical imaging is the ability to use an existing model learned on source data, in a new site. This is known as the domain shift problem. We propose a pseudo labels procedure, which was originally introduced for semi-supervised learning, that is suitable for unsupervised domain adaptation (UDA). We iteratively improve the pseudo labels of the target domain data only using the current pseudo labels without involving the labeled source domain data. We applied our method to several medical MRI image segmentation tasks. We show that, by combining our approach as a post-processing step in standard UDA algorithms, we consistently and significantly improve the segmentation results on test images from the target site.

AB - A well known problem in medical imaging is the ability to use an existing model learned on source data, in a new site. This is known as the domain shift problem. We propose a pseudo labels procedure, which was originally introduced for semi-supervised learning, that is suitable for unsupervised domain adaptation (UDA). We iteratively improve the pseudo labels of the target domain data only using the current pseudo labels without involving the labeled source domain data. We applied our method to several medical MRI image segmentation tasks. We show that, by combining our approach as a post-processing step in standard UDA algorithms, we consistently and significantly improve the segmentation results on test images from the target site.

KW - pseudo labels

KW - site adaptation

KW - transfer learning

KW - unsupervised domain adaptation

UR - http://www.scopus.com/inward/record.url?scp=85172108330&partnerID=8YFLogxK

U2 - 10.1109/isbi53787.2023.10230628

DO - 10.1109/isbi53787.2023.10230628

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85172108330

T3 - Proceedings - International Symposium on Biomedical Imaging

BT - 2023 IEEE International Symposium on Biomedical Imaging, ISBI 2023

PB - IEEE Computer Society

Y2 - 18 April 2023 through 21 April 2023

ER -

PLPP: A Pseudo Labeling Post-Processing Strategy for Unsupervised Domain Adaptation

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this