EUVIMEDEUVIMED entdecken
Crossref

Domain-Specific Bias Filtering for Single Labeled Domain Generalization

Junkun Yuan, Xu Ma, Defang Chen, Kun Kuang, Fei Wu, Lanfen Lin

International Journal of Computer Vision · 2023-02 · 131 (2) · 552-571

DOI: 10.1007/s11263-022-01712-7 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Computer Vision, online erschienen am 24.11.2022. Verfasst von Junkun Yuan und 5 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 94 Literaturangaben. Gefördert von: National Key Research and Development Program of China, Young Elite Scientists Sponsorship Program by CAST, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Conventional Domain Generalization (CDG) utilizes multiple labeled source datasets to train a generalizable model for unseen target domains. However, due to expensive annotation costs, the requirements of labeling all the source data are hard to be met in real-world applications. In this paper, we investigate a Single Labeled Domain Generalization (SLDG) task with only one source domain being labeled, which is more practical and challenging than the CDG task. A major obstacle in the SLDG task is the discriminability-generalization bias: the discriminative information in the labeled source dataset may contain domain-specific bias, constraining the generalization of the trained model. To tackle this challenging task, we propose a novel framework called Domain-Specific Bias Filtering (DSBF), which initializes a discriminative model with the labeled source data and then filters out its domain-specific bias with the unlabeled source data for generalization improvement. We divide the filtering process into (1) feature extractor debiasing via k-means clustering-based semantic feature re-extraction and (2) classifier rectification through attention-guided semantic feature projection. DSBF unifies the exploration of the labeled and the unlabeled source data to enhance the discriminability and generalization of the trained model, resulting in a highly generalizable model. We further provide theoretical analysis to verify the proposed domain-specific bias filtering process. Extensive experiments on multiple datasets show the superior performance of DSBF in tackling both the challenging SLDG task and the CDG task.

Förderung

  • National Key Research and Development Program of China
  • Young Elite Scientists Sponsorship Program by CAST
  • National Natural Science Foundation of China
  • Project by Shanghai AI Laboratory
  • the Starry Night Science Fund of Zhejiang University Shanghai Institute for Advanced Study
  • the Fundamental Research Funds for the Central Universities
  • Natural Science Foundation of Zhejiang Province

Zitieren

APA

Yuan, J., Ma, X., Chen, D., Kuang, K., Wu, F., & Lin, L. (2023). Domain-Specific Bias Filtering for Single Labeled Domain Generalization. International Journal of Computer Vision, 131(2), 552-571. https://doi.org/10.1007/s11263-022-01712-7

Vancouver

Yuan J, Ma X, Chen D, Kuang K, Wu F, Lin L. Domain-Specific Bias Filtering for Single Labeled Domain Generalization. International Journal of Computer Vision. 2023;131(2):552-571. doi:10.1007/s11263-022-01712-7

BibTeX
@article{Yuan2023,
  author = {Yuan, Junkun and Ma, Xu and Chen, Defang and Kuang, Kun and Wu, Fei and Lin, Lanfen},
  title = {Domain-Specific Bias Filtering for Single Labeled Domain Generalization},
  journal = {International Journal of Computer Vision},
  year = {2023},
  volume = {131},
  number = {2},
  pages = {552--571},
  doi = {10.1007/s11263-022-01712-7}
}
Kostenlos starten →