A Theory of Learning Unified Model via Knowledge Integration from Label Space Varying Domains

Dexuan Zhang, Thomas Westfechtel, Tatsuya Harada

CVPR 2025 pp. 10142-10152

doi:10.1109/CVPR52734.2025.00948 /cvpr/2025/zhang2025cvpr-theory/

Abstract

Existing domain adaptation systems can hardly be applied to real-world problems with new classes presenting at deployment time, especially regarding source-free scenarios where multiple source domains do not share the label space despite being given a few labeled target data. To address this, we consider a challenging problem: multi-source semi-supervised open-set domain adaptation and propose a learning theory via joint error, effectively tackling strong domain shift. To generalize the algorithm into source-free cases, we introdcue a computationally efficient and architecture-flexible attention-based feature generation module. Extensive experiments on various data sets demonstrate the significant improvement of our proposed algorithm over baselines.

PDF CVPR Semantic Scholar

Cite

Text

Zhang et al. "A Theory of Learning Unified Model via Knowledge Integration from Label Space Varying Domains." Conference on Computer Vision and Pattern Recognition, 2025. doi:10.1109/CVPR52734.2025.00948

Markdown

[Zhang et al. "A Theory of Learning Unified Model via Knowledge Integration from Label Space Varying Domains." Conference on Computer Vision and Pattern Recognition, 2025.](https://mlanthology.org/cvpr/2025/zhang2025cvpr-theory/) doi:10.1109/CVPR52734.2025.00948

BibTeX

@inproceedings{zhang2025cvpr-theory,
  title     = {{A Theory of Learning Unified Model via Knowledge Integration from Label Space Varying Domains}},
  author    = {Zhang, Dexuan and Westfechtel, Thomas and Harada, Tatsuya},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2025},
  pages     = {10142-10152},
  doi       = {10.1109/CVPR52734.2025.00948},
  url       = {https://mlanthology.org/cvpr/2025/zhang2025cvpr-theory/}
}