Batch Feature Erasing for Person Re-identification and Beyond

11/17/2018 ∙ by Zuozhuo Dai, et al. ∙ 0

This paper presents a new training mechanism called Batch Feature Erasing (BFE) for person re-identification. We apply this strategy to train a novel network with two branches and employing the ResNet-50 as the backbone. The two branches consist of a conventional global branch and a feature erasing branch where the BFE strategy is applied. When training the feature erasing branch, we randomly erase the same region of all the feature maps in a batch. The network then concatenates features from the two branches for person re-identification. Albeit simple, our method achieves state-of-the-art on person re-identification and is applicable to general metric learning tasks in image retrieval problems. For instance, we achieve 75.4 83.0 existed works by a large margin (more than 6

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

page 6

page 8

page 9

page 10

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.