Thermal to Visual Person Re-Identification Using Collaborative Metric Learning Based on Maximum Margin Matrix Factorization. (February 2023)

• Record Type: Journal Article
• Authors: Gavini, Yaswanth; Agarwal, Arun; Mehtre, B.M.
• Is Part Of: Pattern recognition. Volume 134(2023)
• Publication Date: 2023-02
• Subjects: Thermal to visual person re-identification -- Cross-domain image retrieval -- Collaborative metric learning -- Matrix factorization; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2022.109069
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: We address the problem of thermal to visual person re-identification. We propose collaborative metric learning method to address the problem. The proposed collaborative metric learning uses maximum margin matrix factorization. We obtain the more generalised metric due to the maximum margin. Proposed method outperforms the baseline algorithms in few-shot learning settings. Abstract: Thermal to visual person re-identification (T2V-ReID) is a cross-domain image retrieval problem. In this problem, the matching of a person's image takes place, where the image is taken by different cameras (thermal and visual) at different times. This problem has numerous applications in night-time security surveillance. It is challenging due to the large intra-class variations and cross-domain discrepancies. Recently, deep metric learning methods are proposed for this problem. Still, there is a scope to improve the metric learning by generalizing the metric. In this paper, we have proposed the collaborative metric learning using Maximum Margin Matrix Factorization. It uses the group-wise similarities and collaboratively predicts the similarities. We can learn a more generalized metric by utilizing the maximized margin in this method. The proposed method is tested on the RegDB and RGB-D-T data sets, and the method outperforms the existing works in the few-shot learning settings.