%0 Journal Article
%A 高嘉乐
%A 李大湘
%A 李娜
%A 刘颖
%A 武阳阳
%T Saliency guided self-attention network for pedestrian attribute recognition in surveillance scenarios
%D 2022
%R 10.19682/j.cnki.1005-8885.2022.0007
%J 中国邮电高校学报（英文）
%P 21-29
%V 29
%N 5
%X <div style="text-align:justify;">
	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 sel-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.
</div>
<div style="text-align:justify;">
	<br>
</div>
%U https://jcupt.bupt.edu.cn/CN/10.19682/j.cnki.1005-8885.2022.0007