Diversity feature constraint based on heterogeneous data for unsupervised person re-identification. Issue 3 (May 2023)

• Record Type: Journal Article
• Authors: Si, Tongzhen; He, Fazhi; Li, Penglei; Song, Yupeng; Fan, Linkun
• Is Part Of: Information processing & management. Volume 60:Issue 3(2023)
• Publication Date: 2023-05
• Subjects: Unsupervised person re-identification -- Feature optimization -- Clustering -- Heterogeneous data; Information storage and retrieval systems -- Periodicals; Information science -- Periodicals; Systèmes d'information -- Périodiques; Sciences de l'information -- Périodiques; Information science; Information storage and retrieval systems; Periodicals; 658.4038
• DOI: 10.1016/j.ipm.2023.103304
• Languages: English
• ISSNs: 0306-4573

Abstract

Abstract: Person re-identification (ReID) based on heterogeneous data aims to search for the same pedestrian from different modalities. The existing unsupervised heterogeneous ReID method overly relies on pseudo labels and ignores the inter-image feature relationship. In the paper, we propose a novel Diversity Feature Constraint (DFC) method to simultaneously consider the clustering-level and instance-level feature relationship for unsupervised heterogeneous ReID. On the one hand, we employ the clustering algorithm to produce pseudo labels for heterogeneous images. Then, the clustering-level constraint is designed to optimize the model. On the other hand, considering that the clustering algorithm may generate some noise, we propose the complementary intra-modality instance-level constraint to correlate any two intra-modality images. Meanwhile, for eliminating the inter-modality discrepancy, the inter-modality instance-level constraint is developed to decrease the large inter-modality gap. We construct the potential feature relationship between heterogeneous images to constrain the feature distribution. By experiments, we prove that over-reliance on pseudo labels generates limited performance. Exploring inter-image potential relationships is an important way to solve the unsupervised problem. Extensive results demonstrate that DFC achieves superior performance that outperforms other methods by a large margin, improving 15.23% and 9.37% at rank-1 and mAP indexes compared with the clustering method on SYSU-MM01. Highlights: Solve intra/inter-modality distribution forunsupervised heterogeneous ReID. Constrain the feature distribution and compensates for the clustering error. Constraint loss is designed to constrain positive/negative samples. Complete a depth analysis for unsupervised heterogeneous ReID.