Learning refined attribute-aligned network with attribute selection for person re-identification

Yuxuan Shi

doi:10.1016/j.neucom.2020.03.057

2020-08-01

PRE

DOI：10.1016/j.neucom.2020.03.057

原文链接

原文求助

摘要

En 中文

Effective person re-identification (Re-ID) is often required in real applications. While most exiting approaches either assume the detected pedestrian bounding box well-aligned or utilize limited human structural information (pose, attention, segmentation) to calibrate the misalignment. However, the value of utilizing attributes for pedestrian alignment is still under explored. Furthermore, the hierarchy of attributes in previous works has been largely ignored, appearance feature and attribute feature are often fused in a rigid way. This directly limits the discriminatory and robustness of feature representation. In this paper, we propose a Refined Attribute-aligned Network (RAN), which consists of a coarse-alignment and a fine-alignment module. First, the pre-trained part and attribute predictor are used to generate body parts and candidate attributes. Then the body parts are used for coarse alignment and the attributes are selected by an agent. The agent is optimized with policy gradient algorithm, which can maximize the accumulative reward to increase the probability of proper attribute selection. Finally, for the fine-alignment, the attribute maps and body part features are aggregated by a bilinear-pooling layer to support accurate Re-ID. Extensive experimental results based on multiple datasets including CUHK03, DukeMTMC and Market-1501 demonstrate the superiority of our method over state-of-the-art methods. (C) 2020 Elsevier B.V. All rights reserved.

Keyword:

Person re-identification

Attribute-aligned

Attribute selection

Policy gradient