Open-set Mixed Domain Adaptation via visual-linguistic focal evolving
Publication Type
Journal Article
Publication Date
9-2025
Abstract
We introduce a new task, Open-set Mixed Domain Adaptation (OSMDA), which considers the potential mixture of multiple distributions in the target domains, thereby better simulating real-world scenarios. To tackle the semantic ambiguity arising from multiple domains, our key idea is that the linguistic representation can serve as a universal descriptor for samples of the same category across various domains. We thus propose a more practical framework for cross-domain recognition via visual-linguistic guidance. On the other hand, the presence of multiple domains also poses a new challenge in classifying both known and unknown categories. To combat this issue, we further introduce a visual-linguistic focal evolving approach to gradually enhance the classification ability of a known/unknown binary classifier from two aspects. Specifically, we start with identifying highly confident focal samples to expand the pool of known samples by incorporating those from different domains. Then, we amplify the feature discrepancy between known and unknown samples through dynamic entropy evolving via an adaptive entropies min/max game, enabling us to accurately identify possible unknown samples in a gradual manner. Extensive experiments demonstrate our method’s superiority against the state-of-the-arts in both open-set and open-set mixed domain adaptation.
Keywords
Domain adaptation, mixed domain, open-set, visual-linguistics model, entropy evolving
Discipline
Software Engineering
Research Areas
Software and Cyber-Physical Systems
Publication
IEEE Transactions on Circuits and Systems for Video Technology
Volume
35
Issue
9
First Page
8495
Last Page
8507
ISSN
1051-8215
Identifier
10.1109/TCSVT.2025.3551234
Publisher
Institute of Electrical and Electronics Engineers
Citation
LIU, Bangzhen; XU, Yangyang; XU, Cheng; XU, Xuemiao; and HE, Shengfeng.
Open-set Mixed Domain Adaptation via visual-linguistic focal evolving. (2025). IEEE Transactions on Circuits and Systems for Video Technology. 35, (9), 8495-8507.
Available at: https://ink.library.smu.edu.sg/sis_research/10527
Additional URL
https://doi.org/10.1109/TCSVT.2025.3551234