Person Re-Identification Using Additive Distance Constraint With Similar Labels Loss

IEEE Access

Guofa Li¹  Heng Xie¹  Lisha Huang¹  Yaoyu Chen¹  Shen Li²  Chunli Han³  Gang Xu⁴  Liangwen Tang⁵ 

[1] College of Mechatronics and Control Engineering, Institute of Human Factors and Ergonomics, Shenzhen University, Shenzhen, China;Department of Civil and Environmental Engineering, University of Wisconsin&x2013;Hangzhou Nicigo Technology Company Ltd., Hangzhou, China;Madison, Madison, WI, USA;Shenzhen Suanzi Technology Ltd., Shenzhen, China;

关键词: Intelligent safety systems;    person re-identification;    deep learning;    similar labels;    distance constraint;   

DOI  :  10.1109/ACCESS.2020.3023948

来源: DOAJ

【 摘 要 】

Despite the promising progress made in recent years, person re-identification (Re-ID) remains a challenging task due to the intra-class variations. Most of the current studies used the traditional Softmax loss for solutions, but its discriminative capability encounters a bottleneck. Therefore, how to improve person Re-ID performance is still a challenging task. To address this problem, we proposed a novel loss function, namely additive distance constraint with similar labels loss (ADCSLL). Specifically, we reformulated the Softmax loss by adding a distance constraint to the ground truth label, based on which similar labels were introduced to enhance the learned features to be much more stable and centralized. Experimental evaluations were conducted on two popular datasets (Market-1501 and DukeMTMC-reID) to examine the effectiveness of our proposed method. The results showed that our proposed ADCSLL was more discriminative than most of the other compared state-of-the-art methods. The rank-1 accuracy and the mAP on Market-1501 were 95.0% and 87.0%, respectively. The numbers were 88.6% and 77.2% on DukeMTMC-reID, respectively.

【 授权许可】

Unknown