期刊
PATTERN RECOGNITION
卷 126, 期 -, 页码 -出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.patcog.2022.108567
关键词
Person re-identification; Attention learning; Multi-task learning
资金
- National Natural Science Foundation of China [61876180, U2013202, 62076026, 61973029]
- Beijing Natural Science Foundation [4202073]
- Fundamental Research Funds for the Central Universities [FRF-TP-20-08B]
- Guangdong Basic and Applied Basic Research Foundation [2020B1515120050]
This paper proposes a method to predict attention maps in person ReID networks, which includes global and local attention maps to focus on persons and relevant body parts. This method improves the performance of person re-identification.
A B S T R A C T Visual attention has proven to be effective in improving the performance of person re-identification. Most existing methods apply visual attention heuristically by learning an additional attention map to re-weight the feature maps for person re-identification, however, this kind of methods inevitably increase the model complexity and inference time. In this paper, we propose to incorporate the ability of predicting attention maps as additional objectives in a person ReID network without changing the original structure, thus maintain the same inference time and model size. Two kinds of attention maps have been considered to make the learned feature maps being aware of the person and related body parts respectively. Globally, a holistic attention branch (HAB) is proposed to make the feature maps obtained by backbone could focus on persons so as to alleviate the influence of background. Locally, a partial attention branch (PAB) is proposed to make the extracted features can be decoupled into several groups that are separately responsible for different body parts, thus increasing the robustness to pose variation and partial occlusion. These two kinds of attentions are universal and can be incorporated into existing ReID networks. We have tested its performance on two typical networks (TriNet [1] and Bag of Tricks [2]) and observed significant performance improvement on five widely used datasets. (c) 2022 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据