Multi-Task Learning Via Co-Attentive Sharing For Pedestrian Attribute Recognition

Learning to predict multiple attributes of a pedestrian is a multi-task learning problem. To share feature representation between two individual task networks, conventional methods like Cross-Stitch [1] and Sluice [2] network learn a linear combination of features or feature subspaces. However, linear combination rules out the complex interdependency between channels. Moreover, spatial information exchanging is less-considered. In this paper, we propose a novel Co-Attentive Sharing (CAS) module which extracts discriminative channels and spatial regions for more effective feature sharing in multi-task learning. The module consists of three branches, which leverage different channels for between-task feature fusing, attention generation and task-specific feature enhancing, respectively. Experiments on two pedestrian attribute recognition datasets show that our module outperforms the conventional sharing units and achieves superior results compared to the state-of-the-art approaches using many metrics.

[1]  Zhongfei Zhang,et al.  Partially Shared Multi-task Convolutional Neural Network with Local Constraint for Face Attribute Learning , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[2]  Shaogang Gong,et al.  Attribute Recognition by Joint Recurrent Learning of Context and Correlation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[3]  Joachim Bingel,et al.  Sluice networks: Learning what to share between loosely related tasks , 2017, ArXiv.

[4]  黄凯奇,et al.  Multi-attribute Learning for Pedestrian Attribute Recognition in Surveillance Scenarios , 2015 .

[5]  Yan Wang,et al.  Deep View-Sensitive Pedestrian Attribute Inference in an end-to-end Model , 2017, BMVC.

[6]  Xiaoou Tang,et al.  Pedestrian Attribute Recognition At Far Distance , 2014, ACM Multimedia.

[7]  Yifan Sun,et al.  SVDNet for Pedestrian Retrieval , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[8]  Kaiqi Huang,et al.  Pose Guided Deep Model for Pedestrian Attribute Recognition in Surveillance Scenarios , 2018, 2018 IEEE International Conference on Multimedia and Expo (ICME).

[9]  Jaime G. Carbonell,et al.  Characterizing and Avoiding Negative Transfer , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Zhong Ji,et al.  Image-attribute reciprocally guided attention network for pedestrian attribute recognition , 2019, Pattern Recognit. Lett..

[11]  Xiaogang Wang,et al.  HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[12]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Xiaoou Tang,et al.  Learning to Recognize Pedestrian Attribute , 2015, ArXiv.

[14]  Martial Hebert,et al.  Cross-Stitch Networks for Multi-task Learning , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[16]  Liang Zheng,et al.  Improving Person Re-identification by Attribute and Identity Learning , 2017, Pattern Recognit..

[17]  Rama Chellappa,et al.  Attributes for Improved Attributes: A Multi-Task Network Utilizing Implicit and Explicit Relationships for Facial Attribute Classification , 2017, AAAI.

[18]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[19]  Rich Caruana,et al.  Multitask Learning , 1998, Encyclopedia of Machine Learning and Data Mining.

[20]  In-So Kweon,et al.  BAM: Bottleneck Attention Module , 2018, BMVC.

[21]  Junjie Yan,et al.  Localization Guided Learning for Pedestrian Attribute Recognition , 2018, BMVC.

[22]  Xiangyang Xue,et al.  Adaptively Weighted Multi-task Deep Network for Person Attribute Classification , 2017, ACM Multimedia.

[23]  Enhua Wu,et al.  Squeeze-and-Excitation Networks , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  In-So Kweon,et al.  CBAM: Convolutional Block Attention Module , 2018, ECCV.

[25]  Sebastian Ruder,et al.  An Overview of Multi-Task Learning in Deep Neural Networks , 2017, ArXiv.