MHSA-Net: Multi-Head Self-Attention Network for Occluded Person Re-Identification

作     者：Tan, Hongchen Liu, Xiuping Yin, Baocai Li, Xin 

作者机构：Artificial Intelligence Research Institute Beijing University of Technology Beijing100124 China School of Electrical Engineering & Computer Science Center for Computation & Technology Louisiana State University Baton RougeLA70808 United States School of Mathematical Sciences Dalian University of Technology Dalian116024 China 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2020年

核心收录：

主　　题：Machine learning 

摘      要：This paper presents a novel person re-identification model, named Multi-Head Self-Attention Network (MHSA-Net), to prune unimportant information and capture key local information from person images. MHSA-Net contains two main novel components: Multi-Head Self-Attention Branch (MHSAB) and Attention Competition Mechanism (ACM). The MHSAB adaptively captures key local person information, and then produces effective diversity embeddings of an image for the person matching. The ACM further helps filter out attention noise and non-key information. Through extensive ablation studies, we verified that the Multi-Head Self-Attention Branch (MHSAB) and Attention Competition Mechanism (ACM) both contribute to the performance improvement of the MHSA-Net. Our MHSA-Net achieves competitive performance in the standard and occluded person Re-ID tasks. Copyright © 2020, The Authors. All rights reserved.