Consistency-Preserving deep hashing for fast person re-identification. (October 2019)

• Record Type: Journal Article
• Authors: Li, Diangang; Gong, Yihong; Cheng, De; Shi, Weiwei; Tao, Xiaoyu; Chang, Xinyuan
• Is Part Of: Pattern recognition. Volume 94(2019:Oct.)
• Page Start: 207
• Page End: 217
• Publication Date: 2019-10
• Subjects: Convolutional neural network -- Fast person re-identification -- Deep hashing -- Consistency preservation; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2019.05.036
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: We design a new hash structure to guide the hash code learning to be consistent with the high-dimensional feature learning by applying the same softmax classification loss and an improved triplet distance metric learning loss respectively. We propose an effective noise consistency loss to optimize high-dimensional feature learning and hash code extraction in a more robust direction, to keep the prediction of two models same. And these two models are provided with the same image with different noises. We propose a new implementation of topology constraint, which bridge the gap caused by feature binarization, and preserve the topology consistency with ordinal relation and label information. Comprehensive experimental results on the three widely used datasets with various experimental settings demonstrate the superiority of our proposed method. Abstract: Numerous methods have been proposed for person re-identification (Re-ID) with promising performances. While most of them neglect the matching efficiency which is crucial in real-world applications. Recently, several hashing based approaches have been developed, which consider the importance of matching speed in large-scale datasets. Despite the considerable efficiency of these traditional and deep learning based hashing methods, the concomitant matching accuracy reduction is unacceptable in practical application. Towards this end, we propose a novel deep hashing framework, namely Consistency-Preserving Deep Hashing (CPDH), aiming to bridge the gap between the effective high-dimensional feature and low-dimensional binary vector by focusing on the consistency preservation of hash code. First, CPDH designs a new hash structure to extract the hash code. Next, a noise consistency cost is proposed to improve robustness of both hash code and high-dimensional feature. Finally, a topology consistency cost is provided to maintain the ordinal relation between the high-dimensional feature space and Hamming space. Comprehensive experimental results on three widely-used benchmark datasets demonstrate the superior performance of proposed method as compared with existing state-of-the-art approaches.