Unsupervised person re‐identification by part‐compensated soft multi‐label learning. Issue 7 (10th March 2022)

• Record Type: Journal Article
• Authors: Yang, Weiping; Zhang, De
• Is Part Of: IET image processing. Volume 16:Issue 7(2022)
• Page Start: 2012
• Page End: 2024
• Publication Date: 2022-03-10
• Subjects: Image processing -- Periodicals; 621.36705
• DOI: 10.1049/ipr2.12468
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract: Most existing re‐ID models are developed based on supervised learning, which relies on plenty of manually labelled pairwise data for training. However, in many practical applications, such deep re‐ID models are not scalable because of lacking sufficient annotated data. To address this problem, the superiority of unsupervised person re‐ID methods have been reported and become more popular recently. In this paper, an unsupervised framework based on part‐compensated soft multi‐label learning is presented, which aims to explore the potential label information for unlabelled persons through mining both global and part level visual features. This re‐ID framework is mainly composed of global clustering, part clustering and multi‐label assignment. During clustering process, the results of part‐level clustering are compensated into global clustering, allowing the network to learn more detailed information of pedestrians. Meanwhile, fuzzy clustering is used to generate soft multi‐labels instead of commonly used single‐label clustering. To further optimize the model, a cross‐domain excitation parameter is introduced to relieve the background interference arising in the inter‐domain view intersection. The proposed approach is evaluated on three public datasets, including Market‐1501, DukeMTMC‐reID, and MSMT17. Extensive experiments are carried out and this network can outperform the state‐of‐the‐art unsupervised re‐ID models.