EUVIMEDEUVIMED entdecken
Crossref

DM-Adapter: Domain-Aware Mixture-of-Adapters for Text-Based Person Retrieval

Yating Liu, Zimo Liu, Xiangyuan Lan, Wenming Yang, Yaowei Li, Qingmin Liao

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (6) · 5703-5711

DOI: 10.1609/aaai.v39i6.32608 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Yating Liu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 30-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Text-based person retrieval (TPR) has gained significant attention as a fine-grained and challenging task that closely aligns with practical applications. Tailoring CLIP to person domain is now a emerging research topic due to the abundant knowledge of vision-language pretraining, but challenges still remain during fine-tuning: (i) Previous full-model fine-tuning in TPR is computationally expensive and prone to overfitting.(ii) Existing parameter-efficient transfer learning (PETL) for TPR lacks of fine-grained feature extraction. To address these issues, we propose Domain-Aware Mixture-of-Adapters (DM-Adapter), which unifies Mixture-of-Experts (MOE) and PETL to enhance fine-grained feature representations while maintaining efficiency. Specifically, Sparse Mixture-of-Adapters is designed in parallel to MLP layers in both vision and language branches, where different experts specialize in distinct aspects of person knowledge to handle features more finely. To promote the router to exploit domain information effectively and alleviate the routing imbalance, Domain-Aware Router is then developed by building a novel gating function and injecting learnable domain-aware prompts. Extensive experiments show that our DM-Adapter achieves state-of-the-art performance, outperforming previous methods by a significant margin.

Zitieren

APA

Liu, Y., Liu, Z., Lan, X., Yang, W., Li, Y., & Liao, Q. (2025). DM-Adapter: Domain-Aware Mixture-of-Adapters for Text-Based Person Retrieval. Proceedings of the AAAI Conference on Artificial Intelligence, 39(6), 5703-5711. https://doi.org/10.1609/aaai.v39i6.32608

Vancouver

Liu Y, Liu Z, Lan X, Yang W, Li Y, Liao Q. DM-Adapter: Domain-Aware Mixture-of-Adapters for Text-Based Person Retrieval. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(6):5703-5711. doi:10.1609/aaai.v39i6.32608

BibTeX
@article{Liu2025,
  author = {Liu, Yating and Liu, Zimo and Lan, Xiangyuan and Yang, Wenming and Li, Yaowei and Liao, Qingmin},
  title = {DM-Adapter: Domain-Aware Mixture-of-Adapters for Text-Based Person Retrieval},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {6},
  pages = {5703--5711},
  doi = {10.1609/aaai.v39i6.32608}
}
Kostenlos starten →