EUVIMEDEUVIMED entdecken
Crossref

Collaborative Semantic Consistency Alignment for Blended-Target Domain Adaptation

Yuwu Lu, Xue Hu, Waikeung Wong, Haoyu Huang

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (18) · 19170-19179

DOI: 10.1609/aaai.v39i18.34110 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Yuwu Lu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Blended-target domain adaptation (BTDA) leverages learned source knowledge to adapt the model to a blended-target domain that is composed of multiple unlabeled sub-target domains with distinct statistical characteristics. The existing BTDA methods usually overlook semantic correlation information across multiple domains and domain shifts among sub-target domains, resulting in suboptimal adaptation performance. To fully harness semantic knowledge and alleviate domain shifts in hybrid data distribution, we propose a collaborative semantic consistency alignment (CSCA) method for BTDA. Specifically, we achieve distribution alignment by minimizing the sliced Wasserstein distance between the source and target feature distributions. To alleviate complex domain shifts among all sub-target domains in the hybrid feature space, we design graph networks to propagate and share semantic knowledge across domains, which reduces semantic discrepancies among multiple domains. Additionally, we propose a double consistency regularization method to reduce the susceptibility of the model to domain-specific information, further facilitating semantic alignment and alleviating domain shifts. Extensive experiments on several datasets show that CSCA achieves promising classification performance.

Zitieren

APA

Lu, Y., Hu, X., Wong, W., & Huang, H. (2025). Collaborative Semantic Consistency Alignment for Blended-Target Domain Adaptation. Proceedings of the AAAI Conference on Artificial Intelligence, 39(18), 19170-19179. https://doi.org/10.1609/aaai.v39i18.34110

Vancouver

Lu Y, Hu X, Wong W, Huang H. Collaborative Semantic Consistency Alignment for Blended-Target Domain Adaptation. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(18):19170-19179. doi:10.1609/aaai.v39i18.34110

BibTeX
@article{Lu2025,
  author = {Lu, Yuwu and Hu, Xue and Wong, Waikeung and Huang, Haoyu},
  title = {Collaborative Semantic Consistency Alignment for Blended-Target Domain Adaptation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {18},
  pages = {19170--19179},
  doi = {10.1609/aaai.v39i18.34110}
}
Kostenlos starten →