Deep Hybrid Similarity Learning for Person Re-Identification

• Published in: IEEE transactions on circuits and systems for video technology 2018-11, Vol.28 (11), p.3183-3193
• Main Authors: Zhu, Jianqing, Zeng, Huanqiang, Liao, Shengcai, Lei, Zhen, Cai, Canhui, Zheng, Lixin
• Format: Article
• Language: English
• Subjects: Convolution; convolution neural network; Correlation; deep hybrid similarity learning; DH-HEMTs; Euclidean distance; Feature extraction; Learning; Metric learning; Multiplication; Neural networks; person re-identification (Re-ID); Similarity; State of the art; Weight
• ISSN: 1051-8215; 1558-2205
• DOI: 10.1109/TCSVT.2017.2734740

Person re-identification (Re-ID) aims to match person images captured from two non-overlapping cameras. In this paper, a deep hybrid similarity learning (DHSL) method for person Re-ID based on a convolution neural network (CNN) is proposed. In our approach, a light CNN learning feature pair for the input image pair is simultaneously extracted. Then, both the elementwise absolute difference and multiplication of the CNN learning feature pair are calculated. Finally, a hybrid similarity function is designed to measure the similarity between the feature pair, which is realized by learning a group of weight coefficients to project the elementwise absolute difference and multiplication into a similarity score. Consequently, the proposed DHSL method is able to reasonably assign complexities of feature learning and metric learning in a CNN, so that the performance of person Re-ID is improved. Experiments on three challenging person Re-ID databases, QMUL GRID, VIPeR, and CUHK03, illustrate that the proposed DHSL method is superior to multiple state-of-the-art person Re-ID methods.