Domain-Guided Weight Modulation for Semi-Supervised Domain Generalization
Galappaththige, Chamuditha Jayanaga Izzo, Zachary He, Xilin Zhou, Honglu Khan, Muhammad Haris
Galappaththige, Chamuditha Jayanaga
Izzo, Zachary
He, Xilin
Zhou, Honglu
Khan, Muhammad Haris
Supervisor
Department
Computer Vision
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Unarguably, deep learning models capable of generalizing to unseen domain data while leveraging a few labels are of great practical significance due to low developmental costs. In search of this endeavor, we study the challenging problem of semi-supervised domain generalization (SSDG), where the goal is to learn a domain-generalizable model while using only a small fraction of labeled data and a relatively large fraction of unlabeled data. Domain generalization (DG) methods show subpar performance under the SSDG setting, whereas semi-supervised learning (SSL) methods demonstrate relatively better performance, however, they are considerably poor compared to the fully-supervised DG methods. Towards handling this new, but challenging problem of SSDG, we propose a novel method that can facilitate the generation of accurate pseudo-labels under various domain shifts. This is accomplished by retaining the domain-level specialism in the classifier during training corresponding to each source domain. Specifically, we first create domain-level information vectors on the fly which are then utilized to learn a domain-aware mask for modulating the classifier's weights. We provide a mathematical interpretation for the effect of this modulation procedure on both pseudo-labeling and model training. Our method is plug-and-play and can be readily applied to different SSL baselines for SSDG. Extensive experiments on six challenging datasets in two different SSDG settings show that our method provides visible gains over the various strong SSL-based SSDG baselines. Our code is available at github.com/DGWM.
Citation
C. J. Galappaththige, Z. Izzo, X. He, H. Zhou and M. H. Khan, "Domain-Guided Weight Modulation for Semi-Supervised Domain Generalization," 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, AZ, USA, 2025, pp. 6495-6505, doi: 10.1109/WACV61041.2025.00633.
Source
Proceedings - 2025 IEEE Winter Conference on Applications of Computer Vision, WACV 2025
Conference
2025 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2025
Keywords
Subjects
Source
2025 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2025
Publisher
IEEE