You only label once: A self‐adaptive clustering‐based method for source‐free active domain adaptation

Abstract With the growing significance of data privacy protection, Source‐Free Domain Adaptation (SFDA) has gained attention as a research topic that aims to transfer knowledge from a labeled source domain to an unlabeled target domain without accessing source data. However, the absence of source da...

Full description

Bibliographic Details
Main Authors: Zhishu Sun, Luojun Lin, Yuanlong Yu
Format: Article
Language:English
Published: Wiley 2024-04-01
Series:IET Image Processing
Subjects:
Online Access:https://doi.org/10.1049/ipr2.13025
_version_ 1797216931202203648
author Zhishu Sun
Luojun Lin
Yuanlong Yu
author_facet Zhishu Sun
Luojun Lin
Yuanlong Yu
author_sort Zhishu Sun
collection DOAJ
description Abstract With the growing significance of data privacy protection, Source‐Free Domain Adaptation (SFDA) has gained attention as a research topic that aims to transfer knowledge from a labeled source domain to an unlabeled target domain without accessing source data. However, the absence of source data often leads to model collapse or restricts the performance improvements of SFDA methods, as there is insufficient true‐labeled knowledge for each category. To tackle this, Source‐Free Active Domain Adaptation (SFADA) has emerged as a new task that aims to improve SFDA by selecting a small set of informative target samples labeled by experts. Nevertheless, existing SFADA methods impose a significant burden on human labelers, requiring them to continuously label a substantial number of samples throughout the training period. In this paper, a novel approach is proposed to alleviate the labeling burden in SFADA by only necessitating the labeling of an extremely small number of samples on a one‐time basis. Moreover, considering the inherent sparsity of these selected samples in the target domain, a Self‐adaptive Clustering‐based Active Learning (SCAL) method is proposed that propagates the labels of selected samples to other datapoints within the same cluster. To further enhance the accuracy of SCAL, a self‐adaptive scale search method is devised that automatically determines the optimal clustering scale, using the entropy of the entire target dataset as a guiding criterion. The experimental evaluation presents compelling evidence of our method's supremacy. Specifically, it outstrips previous SFDA methods, delivering state‐of‐the‐art (SOTA) results on standard benchmarks. Remarkably, it accomplishes this with less than 0.5% annotation cost, in stark contrast to the approximate 5% required by earlier techniques. The approach thus not only sets new performance benchmarks but also offers a markedly more practical and cost‐effective solution for SFADA, making it an attractive choice for real‐world applications where labeling resources are limited.
first_indexed 2024-04-24T11:53:48Z
format Article
id doaj.art-dff4ce55e7c14e318ed3e3d69abdda4b
institution Directory Open Access Journal
issn 1751-9659
1751-9667
language English
last_indexed 2024-04-24T11:53:48Z
publishDate 2024-04-01
publisher Wiley
record_format Article
series IET Image Processing
spelling doaj.art-dff4ce55e7c14e318ed3e3d69abdda4b2024-04-09T06:07:10ZengWileyIET Image Processing1751-96591751-96672024-04-011851268128210.1049/ipr2.13025You only label once: A self‐adaptive clustering‐based method for source‐free active domain adaptationZhishu Sun0Luojun Lin1Yuanlong Yu2College of Computer and Data Science Fuzhou University Fuzhou ChinaCollege of Computer and Data Science Fuzhou University Fuzhou ChinaCollege of Computer and Data Science Fuzhou University Fuzhou ChinaAbstract With the growing significance of data privacy protection, Source‐Free Domain Adaptation (SFDA) has gained attention as a research topic that aims to transfer knowledge from a labeled source domain to an unlabeled target domain without accessing source data. However, the absence of source data often leads to model collapse or restricts the performance improvements of SFDA methods, as there is insufficient true‐labeled knowledge for each category. To tackle this, Source‐Free Active Domain Adaptation (SFADA) has emerged as a new task that aims to improve SFDA by selecting a small set of informative target samples labeled by experts. Nevertheless, existing SFADA methods impose a significant burden on human labelers, requiring them to continuously label a substantial number of samples throughout the training period. In this paper, a novel approach is proposed to alleviate the labeling burden in SFADA by only necessitating the labeling of an extremely small number of samples on a one‐time basis. Moreover, considering the inherent sparsity of these selected samples in the target domain, a Self‐adaptive Clustering‐based Active Learning (SCAL) method is proposed that propagates the labels of selected samples to other datapoints within the same cluster. To further enhance the accuracy of SCAL, a self‐adaptive scale search method is devised that automatically determines the optimal clustering scale, using the entropy of the entire target dataset as a guiding criterion. The experimental evaluation presents compelling evidence of our method's supremacy. Specifically, it outstrips previous SFDA methods, delivering state‐of‐the‐art (SOTA) results on standard benchmarks. Remarkably, it accomplishes this with less than 0.5% annotation cost, in stark contrast to the approximate 5% required by earlier techniques. The approach thus not only sets new performance benchmarks but also offers a markedly more practical and cost‐effective solution for SFADA, making it an attractive choice for real‐world applications where labeling resources are limited.https://doi.org/10.1049/ipr2.13025computer visionimage recognition
spellingShingle Zhishu Sun
Luojun Lin
Yuanlong Yu
You only label once: A self‐adaptive clustering‐based method for source‐free active domain adaptation
IET Image Processing
computer vision
image recognition
title You only label once: A self‐adaptive clustering‐based method for source‐free active domain adaptation
title_full You only label once: A self‐adaptive clustering‐based method for source‐free active domain adaptation
title_fullStr You only label once: A self‐adaptive clustering‐based method for source‐free active domain adaptation
title_full_unstemmed You only label once: A self‐adaptive clustering‐based method for source‐free active domain adaptation
title_short You only label once: A self‐adaptive clustering‐based method for source‐free active domain adaptation
title_sort you only label once a self adaptive clustering based method for source free active domain adaptation
topic computer vision
image recognition
url https://doi.org/10.1049/ipr2.13025
work_keys_str_mv AT zhishusun youonlylabelonceaselfadaptiveclusteringbasedmethodforsourcefreeactivedomainadaptation
AT luojunlin youonlylabelonceaselfadaptiveclusteringbasedmethodforsourcefreeactivedomainadaptation
AT yuanlongyu youonlylabelonceaselfadaptiveclusteringbasedmethodforsourcefreeactivedomainadaptation