Triplet erasing-based data augmentation for person re-identification Online publication date: Mon, 14-Dec-2020
by Wei Sun; Xu Zhang; Xiaorui Zhang; Guoce Zhang; Nannan Ge
International Journal of Sensor Networks (IJSNET), Vol. 34, No. 4, 2020
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.
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Sensor Networks (IJSNET):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email subs@inderscience.com
Our Blog 
Follow us on Twitter 
Visit us on Facebook