Open Access

ARTICLE

Enhancing Unsupervised Domain Adaptation for Person Re-Identification with the Minimal Transfer Cost Framework

by Sheng Xu¹, Shixiong Xiang², Feiyu Meng¹, Qiang Wu^1,*

1 Research Institute of Electronic Science and Technology, University of Electronic Science and Technology of China, Chengdu, 610000, China
2 National Key Laboratory of Optical Field Manipulation Science and Technology, Chinese Academy of Sciences, Chengdu, 610209, China

* Corresponding Author: Qiang Wu. Email:

Computers, Materials & Continua 2024, 80(3), 4197-4218. https://doi.org/10.32604/cmc.2024.055157

Received 19 June 2024; Accepted 05 August 2024; Issue published 12 September 2024

Abstract

In Unsupervised Domain Adaptation (UDA) for person re-identification (re-ID), the primary challenge is reducing the distribution discrepancy between the source and target domains. This can be achieved by implicitly or explicitly constructing an appropriate intermediate domain to enhance recognition capability on the target domain. Implicit construction is difficult due to the absence of intermediate state supervision, making smooth knowledge transfer from the source to the target domain a challenge. To explicitly construct the most suitable intermediate domain for the model to gradually adapt to the feature distribution changes from the source to the target domain, we propose the Minimal Transfer Cost Framework (MTCF). MTCF considers all scenarios of the intermediate domain during the transfer process, ensuring smoother and more efficient domain alignment. Our framework mainly includes three modules: Intermediate Domain Generator (IDG), Cross-domain Feature Constraint Module (CFCM), and Residual Channel Space Module (RCSM). First, the IDG Module is introduced to generate all possible intermediate domains, ensuring a smooth transition of knowledge from the source to the target domain. To reduce the cross-domain feature distribution discrepancy, we propose the CFCM Module, which quantifies the difficulty of knowledge transfer and ensures the diversity of intermediate domain features and their semantic relevance, achieving alignment between the source and target domains by incorporating mutual information and maximum mean discrepancy. We also design the RCSM, which utilizes attention mechanism to enhance the model’s focus on personnel features in low-resolution images, improving the accuracy and efficiency of person re-ID. Our proposed method outperforms existing technologies in all common UDA re-ID tasks and improves the Mean Average Precision (mAP) by 2.3% in the Market to Duke task compared to the state-of-the-art (SOTA) methods.

---

Keywords

---