cs.CVNov 9, 2026

MDA framework: multi-architecture domain adaptation for unsupervised person re-identification

Authors: Wei Zhang, Peijun Ye, Dihu Chen, Tao Su

Organizations: School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, Guangdong, China · Peng Cheng Laboratory, Shenzhen, Guangdong, China · School of Integrated Circuits, Sun Yat-sen University, Shenzhen, Guangdong, China

Abstract

Unsupervised person re-identification not only faces the challenge of domain gaps, but existing methods also rarely support multiple network architectures. To tackle both issues, this paper proposes a multi-architecture auto-adaptive domain adaptation method: Mamba augmented multi-architecture domain adaptation framework. Specifically, this paper constructs the multi-architecture domain adaptation capability at two levels. At the first level, we propose a composite operator(MDA operator) that encapsulates Mamba as a component for enhancing domain adaptation. At the second level, based on this operator, we propose a Mamba-enhanced multi-architecture Domain Adaptation framework(MDA framework). Comprehensive experiments on person re-identification benchmarks validate the consistency and flexibility of the proposed framework. The MDA framework supports versatile deployment strategies without being confined to a single integration point. Under a single deployment configuration, it surpasses several SOTA methods. Moreover, it demonstrates substantial performance improvements across both CNN and Transformer architectures. When embedded into a CNN backbone, the framework achieves a 10.2% mAP improvement on the adaptation task from CUHK03 to Market-1501. Integrated with a Transformer backbone, it yields a 19.8% mAP improvement on the same task.

Figures & tables

Explore similar work

CardsList
  1. AIDA-ReID: Adaptive Intermediate Domain Adaptation for Generalizable and Source-Free Person Re-Identification

    Apr 30, 2026Sundas Iqbal, Qing Tian, Danish Ali +2Multi-Source Domain AdaptationSource-Free Domain Adaptation

  2. Confidence-Guided Pseudo-Label Refinement for Unsupervised Cross-Domain Person Re-Identification

    Oct 19, 2026Sundas Iqbal, Danish Ali, Qing Tian +3Person Re-IdentificationUnsupervised Domain Adaptation

  3. Multimodal LLM-Empowered Re-Ranking for Generalizable Person Re-Identification

    Jun 15, 2026Jiachen Li, Xiaojin GongMultimodal RerankingMultimodal Large Language Models