EUVIMEDEUVIMED entdecken
Crossref

Leveraging Mixture Alignment for Multi-Source Domain Adaptation

Aveen Dayal, S Shrusti, Linga Reddy Cenkeramaddi, C Krishna Mohan, Abhinav Kumar

IEEE Transactions on Image Processing · 2025 · 34 · 885-898

DOI: 10.1109/tip.2025.3532094 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2025. Verfasst von Aveen Dayal und 4 weiteren Autor:innen. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 67 Literaturangaben. Gefördert von: Prime Minister Research Fellowship (PMRF), Ministry of Education (MoE), Government of India.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In a conventional Domain Adaptation (DA) setting, we only have one source and target domain, whereas, in many real-world applications, data is often collected from several related sources in different conditions. This has led to a more practical and challenging knowledge transfer problem called Multi-source Domain Adaptation (MDA). Several methodologies, such as prototype matching, explicit distance discrepancy, adversarial learning, etc., have been considered to tackle the MDA problem in recent years. Among them, the adversarial-based learning framework is a popular methodology for transferring knowledge from multiple sources to target domains using a minmax optimization strategy. Despite the advances in adversarial-based methods, several limitations exist, such as the need for a classifier-aware discrepancy metric to align the domains and the need to consider target samples' consistency and semantic information while aligning the domains. To mitigate these issues, in this work, we propose a novel adversarial learning MDA algorithm, MDAMA, which aligns the target domain with a mixture distribution that consists of source domains. MDAMA uses margin-based discrepancy and augmented intermediate distributions to align the domains effectively. We also propose consistency of target samples by confidence thresholding and transfer of semantic information from multiple source domains to the augmented target domain to further improve the performance of the target domain. We extensively experiment with the MDAMA algorithm on popular real-world MDA datasets such as OfficeHome, Office31, PACS, Office-Caltech, and DomainNet. We evaluate the MDAMA model on these benchmark datasets and demonstrate top performance in all of them.

Förderung

  • Prime Minister Research Fellowship (PMRF), Ministry of Education (MoE), Government of India

Zitieren

APA

Dayal, A., Shrusti, S., Cenkeramaddi, L. R., Krishna Mohan, C., & Kumar, A. (2025). Leveraging Mixture Alignment for Multi-Source Domain Adaptation. IEEE Transactions on Image Processing, 34, 885-898. https://doi.org/10.1109/tip.2025.3532094

Vancouver

Dayal A, Shrusti S, Cenkeramaddi LR, Krishna Mohan C, Kumar A. Leveraging Mixture Alignment for Multi-Source Domain Adaptation. IEEE Transactions on Image Processing. 2025;34:885-898. doi:10.1109/tip.2025.3532094

BibTeX
@article{Dayal2025,
  author = {Dayal, Aveen and Shrusti, S and Cenkeramaddi, Linga Reddy and Krishna Mohan, C and Kumar, Abhinav},
  title = {Leveraging Mixture Alignment for Multi-Source Domain Adaptation},
  journal = {IEEE Transactions on Image Processing},
  year = {2025},
  volume = {34},
  pages = {885--898},
  doi = {10.1109/tip.2025.3532094}
}
Kostenlos starten →