Saliency guided self-attention network for pedestrian attribute recognition in surveillance scenarios  

作　　者：Li Na Wu Yangyang Liu Ying Li Daxiang Gao Jiale 

机构地区：[1]School of Communication and Information Engineering,Xi'an University of Posts and Telecommunications,Xi'an 710121,China [2]Key Laboratory of Electronic Information Application Technology for Scene Investigation,Xi'an University of Posts and Telecommunications,Xian 710121,China

出　　处：《The Journal of China Universities of Posts and Telecommunications》2022年第5期21-29,共9页中国邮电高校学报（英文版）

基　　金：supported by the National Natural Science Foundation of China (41874173)。

摘　　要：Pedestrian attribute recognition is often considered as a multi-label image classification task. In order to make full use of attribute-related location information, a saliency guided self-attention network(SGSA-Net) was proposed to weakly supervise attribute localization, without annotations of attribute-related regions. Saliency priors were integrated into the spatial attention module(SAM). Meanwhile, channel-wise attention and spatial attention were introduced into the network. Moreover, a weighted binary cross-entropy loss(WCEL) function was employed to handle the imbalance of training data. Extensive experiments on richly annotated pedestrian(RAP) and pedestrian attribute(PETA) datasets demonstrated that SGSA-Net outperformed other state-of-the-art methods.

关 键 词：pedestrian attribute recognition saliency detection self-attention mechanism 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]