Title: Triplet erasing-based data augmentation for person re-identification

Authors: Wei Sun; Xu Zhang; Xiaorui Zhang; Guoce Zhang; Nannan Ge

Addresses: Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment Technology, Nanjing University of Information Science and Technology, Nanjing, 210044, Jiangsu, China ' School of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, China ' Jiangsu Engineering Center of Network Monitoring, Nanjing University of Information Science and Technology, Nanjing, 210044, Jiangsu, China ' School of Automation, Nanjing University of Information Science & Technology, Nanjing 210044, China ' School of Automation, Nanjing University of Information Science & Technology, Nanjing 210044, China

Abstract: Occlusion is a fundamental but challenging problem in person re-identification. Previous work like random erasing randomly selects a rectangle region in an image and erases its pixels with random values without considering the correlation between images when triplet loss is employed. To address the problem, we propose an end-to-end approach called triplet erasing-based data augmentation for person re-identification (ReID). We apply this approach to train a convolutional neural network (CNN) with two branches. Local distance branch determines the location of the part that needs to be erased in the image, and then triplet erasing branch erases a rectangle region in the determined part. By generating a variety of occlusion samples, triplet erasing improves the robustness of the model against occlusion. Triplet erasing can increase the distance between the positive sample pairs and decrease the distance between the negative sample pairs, thereby improving the generalisation ability of the network.

Keywords: deep learning; person re-identification; data augmentation; convolutional neural network; ResNet-50; triplet loss; occlusion.

DOI: 10.1504/IJSNET.2020.111782

International Journal of Sensor Networks, 2020 Vol.34 No.4, pp.226 - 235

Received: 20 Mar 2020
Accepted: 09 May 2020

Published online: 14 Dec 2020 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article