激光与光电子学进展, 2020, 57 (20): 201001, 网络出版: 2020-10-13
基于多尺度注意力机制的多分支行人重识别算法 下载: 1175次
Multi-Branch Person Re-Identification Based on Multi-Scale Attention
图像处理 深度学习 行人重识别 注意力机制 多尺度特征 局部特征 image processing deep learning person re-identification attention multi-scale feature local feature
摘要
针对基于深度学习的传统方法对于次显著细节信息关注不足的问题,提出一种基于多尺度注意力机制的多分支网络来统筹图像的显著信息及次显著信息。首先,将多尺度特征融合方法(MSFF)与注意力机制相结合,设计了一个多尺度注意力模块(MSA),使得网络可以根据输入信息自适应地调节感受野大小,实现了对于不同尺度信息的充分利用。其次,建立一个多分支网络,实现对于全局特征和多元局部特征的协调统一,并利用多尺度注意力模块,分别实现对于全局显著信息及次显著局部细节信息的加权强化,得到更具判别性的特征用于最终的识别。实验结果表明,本文所设计的网络在多个数据集上都取得了较好的表现。
Abstract
The traditional method based on deep learning does not focus on sub-significant information. Therefore, a multi-branch network based on multi-scale attention (MSA) mechanism was proposed to coordinate significant and sub-significant information. Firstly, the proposed algorithm combined the multi-scale feature fusion module (MSFF) with the attention mechanism to get an MSA module. This module enables the network to adaptively adjust the size of the receptive field according to the input information so as to make full use of information of different scales. Additionally, a multi-branch network was established to realize the coordination of global features and multiple local features. Using the MSA module, weighted enhancement of global information and local detail information can be achieved separately, and a more discriminative feature is obtained for final recognition. The experiment results show that the proposed method performs well on multiple datasets.
李聪, 蒋敏, 孔军. 基于多尺度注意力机制的多分支行人重识别算法[J]. 激光与光电子学进展, 2020, 57(20): 201001. Cong Li, Min Jiang, Jun Kong. Multi-Branch Person Re-Identification Based on Multi-Scale Attention[J]. Laser & Optoelectronics Progress, 2020, 57(20): 201001.