Pedestrian attribute recognition in surveillance scenarios is still a challenging task due to the inaccurate localization of specific attributes. In this paper, we propose a novel view-attribute localization method ba...Pedestrian attribute recognition in surveillance scenarios is still a challenging task due to the inaccurate localization of specific attributes. In this paper, we propose a novel view-attribute localization method based on attention(VALA), which utilizes view information to guide the recognition process to focus on specific attributes and attention mechanism to localize specific attribute-corresponding areas. Concretely, view information is leveraged by the view prediction branch to generate four view weights that represent the confidences for attributes from different views. View weights are then delivered back to compose specific view-attributes, which will participate and supervise deep feature extraction. In order to explore the spatial location of a view-attribute, regional attention is introduced to aggregate spatial information and encode inter-channel dependencies of the view feature. Subsequently, a fine attentive attribute-specific region is localized, and regional weights for the view-attribute from different spatial locations are gained by the regional attention. The final view-attribute recognition outcome is obtained by combining the view weights with the regional weights. Experiments on three wide datasets(richly annotated pedestrian(RAP), annotated pedestrian v2(RAPv2), and PA-100 K) demonstrate the effectiveness of our approach compared with state-of-the-art methods.展开更多
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) ...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.展开更多
文摘针对先前研究工作对行人属性相关性分析不足和行人图像中细粒度属性特征难以捕获的问题,首先基于关联规则寻找属性之间的相关性,然后根据相关性改变网络结构,提升有较强相关性属性的准确率并嵌入改进的HSA(hierarchy split attention)注意力模块,将特征图中的潜在信息进行深度挖掘.HSA注意力模块将特征图进行分组和在子特征图之间增加通道交互操作,整合后的特征图输入挤压激励(squeeze and excitation,SE)模块中,提取图像在通道上的信息.在PA100K、Market-1501和PETA数据集上的实验结果表明,本算法的精确率、召回率、F1值与其他算法相当,但是准确率有较大提升.
基金supported by National Key R&D Program of China(No.2018YFB1308000)Natural Science Foundation of Zhejiang province(No.LY21F 030018)。
文摘Pedestrian attribute recognition in surveillance scenarios is still a challenging task due to the inaccurate localization of specific attributes. In this paper, we propose a novel view-attribute localization method based on attention(VALA), which utilizes view information to guide the recognition process to focus on specific attributes and attention mechanism to localize specific attribute-corresponding areas. Concretely, view information is leveraged by the view prediction branch to generate four view weights that represent the confidences for attributes from different views. View weights are then delivered back to compose specific view-attributes, which will participate and supervise deep feature extraction. In order to explore the spatial location of a view-attribute, regional attention is introduced to aggregate spatial information and encode inter-channel dependencies of the view feature. Subsequently, a fine attentive attribute-specific region is localized, and regional weights for the view-attribute from different spatial locations are gained by the regional attention. The final view-attribute recognition outcome is obtained by combining the view weights with the regional weights. Experiments on three wide datasets(richly annotated pedestrian(RAP), annotated pedestrian v2(RAPv2), and PA-100 K) demonstrate the effectiveness of our approach compared with state-of-the-art methods.
基金supported by the National Natural Science Foundation of China (41874173)。
文摘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.
