Beyond Triplet Loss: Person Re-Identification With Fine-Grained Difference-Aware Pairwise Loss

• Published in: IEEE transactions on multimedia Vol. 24; pp. 1665 - 1677
• Main Authors: Yan, Cheng, Pang, Guansong, Bai, Xiao, Liu, Changhong, Ning, Xin, Gu, Lin, Zhou, Jun
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Benchmark testing; Feature extraction; Fine-grained difference; Gallium nitride; Identities; pairwise loss; person re-identification; Pose estimation; representation learning; Semantics; Task analysis; Training; triplet loss
• ISSN: 1520-9210; 1941-0077
• DOI: 10.1109/TMM.2021.3069562

Person Re-IDentification (ReID) aims at re-identifying persons from different viewpoints across multiple cameras. Capturing the fine-grained appearance differences is often the key to accurate person ReID, because many identities can be differentiated only when looking into these fine-grained differences. However, most state-of-the-art person ReID approaches, typically driven by a triplet loss, fail to effectively learn the fine-grained features as they are focused more on differentiating large appearance differences. To address this issue, we introduce a novel pairwise loss function that enables ReID models to learn the fine-grained features by adaptively enforcing an exponential penalization on the images of small differences and a bounded penalization on the images of large differences. The proposed loss is generic and can be used as a plugin to replace the triplet loss to significantly enhance different types of state-of-the-art approaches. Experimental results on four benchmark datasets show that the proposed loss substantially outperforms a number of popular loss functions by large margins; and it also enables significantly improved data efficiency.