AANet: Attribute Attention Network for Person Re-Identifications

12/19/2019
by   Chiat-Pin Tay, et al.
33

This paper proposes Attribute Attention Network (AANet), a new architecture that integrates person attributes and attribute attention maps into a classification framework to solve the person re-identification (re-ID) problem. Many person re-ID models typically employ semantic cues such as body parts or human pose to improve the re-ID performance. Attribute information, however, is often not utilized. The proposed AANet leverages on a baseline model that uses body parts and integrates the key attribute information in an unified learning framework. The AANet consists of a global person ID task, a part detection task and a crucial attribute detection task. By estimating the class responses of individual attributes and combining them to form the attribute attention map (AAM), a very strong discriminatory representation is constructed. The proposed AANet outperforms the best state-of-the-art method arXiv:1711.09349v3 [cs.CV] using ResNet-50 by 3.36 dataset. On Market1501 dataset, AANet achieves 92.38 accuracy with re-ranking, outperforming arXiv:1804.00216v1 [cs.CV], another state of the art method using ResNet-152, by 1.42 accuracy. In addition, AANet can perform person attribute prediction (e.g., gender, hair length, clothing length etc.), and localize the attributes in the query image.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset