Large margin relative distance learning for person re‐identification. Issue 6 (22nd June 2017)

• Record Type: Journal Article
• Authors: Dong, Husheng; Gong, Shengrong; Liu, Chunping; Ji, Yi; Zhong, Shan
• Is Part Of: IET computer vision. Volume 11:Issue 6(2017)
• Page Start: 455
• Page End: 462
• Publication Date: 2017-06-22
• Subjects: gradient methods -- learning (artificial intelligence) -- pedestrians -- image matching; large margin relative distance learning -- person reidentification -- distance metric learning -- imbalanced data -- LMRDL -- triplet constraints -- imbalanced sample pairs -- logistic metric learning problem -- optimisation scheme -- proximal gradient approach; Computer vision -- Periodicals; Pattern recognition systems -- Periodicals; 006.37
• DOI: 10.1049/iet-cvi.2016.0265
• Languages: English
• ISSNs: 1751-9632

Abstract

Abstract : Distance metric learning has achieved great success in person re‐identification. Most existing methods that learn metrics from pairwise constraints suffer the problem of imbalanced data. In this study, the authors present a large margin relative distance learning (LMRDL) method which learns the metric from triplet constraints, so that the problem of imbalanced sample pairs can be bypassed. Different from existing triplet‐based methods, LMRDL employs an improved triplet loss that enforces penalisation on the triplets with minimal inter‐class distance, and this leads to a more stringent constraint to guide the learning. To suppress the large variations of pedestrian's appearance in different camera views, the authors propose to learn the metric over the intra‐class subspace. The proposed method is formulated as a logistic metric learning problem with positive semi‐definite constraint, and the authors derive an efficient optimisation scheme to solve it based on the accelerated proximal gradient approach. Experimental results show that the proposed method achieves state‐of‐the‐art performance on three challenging datasets (VIPeR, PRID450S, and GRID).