{"type":"ScholarlyArticle","title":"A Solution to Co-occurence Bias: Attributes Disentanglement via Mutual Information Minimization for Pedestrian Attribute Recognition","authors":[{"name":"Yibo Zhou","slug":"yibo-zhou","given":"Yibo","family":"Zhou","affiliation":"State key laboratory of virtual reality technology and systems , Beihang University"},{"name":"Hai-Miao Hu","slug":"hai-miao-hu","given":"Hai-Miao","family":"Hu","affiliation":"State key laboratory of virtual reality technology and systems , Beihang University; Hangzhou Innovation Institute , Beihang University"},{"name":"Jinzuo Yu","slug":"jinzuo-yu","given":"Jinzuo","family":"Yu","affiliation":"State key laboratory of virtual reality technology and systems , Beihang University"},{"name":"Zhenbo Xu","slug":"zhenbo-xu","given":"Zhenbo","family":"Xu","affiliation":"Hangzhou Innovation Institute , Beihang University"},{"name":"Weiqing Lu","slug":"weiqing-lu","given":"Weiqing","family":"Lu","affiliation":"State key laboratory of virtual reality technology and systems , Beihang University"},{"name":"Yuran Cao","slug":"yuran-cao","given":"Yuran","family":"Cao","affiliation":"State key laboratory of virtual reality technology and systems , Beihang University"}],"abstract":"Recent studies on pedestrian attribute recognition progress with either explicit or implicit modeling of the co-occurence among attributes. Considering that this known a prior is highly variable and unforeseeable regarding the specific scenarios, we show that current methods can actually suffer in generalizing such fitted attributes interdependencies onto scenes or identities off the dataset distribution, resulting in the underlined bias of attributes co-occurence. To render models robust in realistic scenes, we propose the attributes-disentangled feature learning to ensure the recognition of an attribute not inferring on the existence of others, and which is sequentially formulated as a problem of mutual information minimization. Rooting from it, practical strategies are devised to efficiently decouple attributes, which substantially improve the baseline and establish state-of-the-art performance on realistic datasets like PETAzs and RAPzs.","doi":"10.24963/ijcai.2023/203","url":"https://ijcai.org/proceedings/2023/203","pdf":"https://ijcai.org/proceedings/2023/0203.pdf","markdown":"https://ijcai.org/proceedings/2023/203.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/203","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Computer Vision","track":"Main Track","number":203,"pages":{"first":1831,"last":1839},"keywords":["Computer Vision: CV: Bias, fairness and privacy","Computer Vision: CV: Recognition (object detection, categorization)"],"videos":[],"references":[{"position":1,"raw":"[Chen et al., 2019] Zhiyuan Chen, Annan Li, and Yunhong Wang. A temporal attentive approach for video-based pedestrian attribute recognition. In Pattern Recognition and Computer Vision: Second Chinese Conference, PRCV 2019, Xi'an, China, November 8-11, 2019, Proceedings, Part II 2, pages 209-220. Springer, 2019.","title":"A temporal attentive approach for video-based pedestrian attribute recognition","authors":"Zhiyuan Chen, Annan Li, Yunhong Wang","year":"2019","venue":"Pattern Recognition and Computer Vision: Second Chinese Conference, PRCV 2019","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Deng et al., 2014] Y. Deng, L. Ping, C. L. Chen, and X. Tang. Pedestrian attribute recognition at far distance. ACM, 2014.","title":"Pedestrian attribute recognition at far distance","authors":"Y Deng, L Ping, C L Chen, X Tang","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Fabbri et al., 2017] Matteo Fabbri, Simone Calderara, and Rita Cucchiara. Generative adversarial models for people attribute recognition in surveillance. In 2017 14th IEEE international conference on advanced video and signal based surveillance (AVSS), pages 1-6. IEEE, 2017.","title":"Generative adversarial models for people attribute recognition in surveillance","authors":"Matteo Fabbri, Simone Calderara, Rita Cucchiara","year":"2017","venue":"14th IEEE international conference on advanced video and signal based surveillance (AVSS)","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Fan et al., 2020] H. Fan, H. M. Hu, S. Liu, W. Lu, and S. Pu. Correlation graph convolutional network for pedestrian at- tribute recognition. IEEE Transactions on Multimedia, PP(99):1-1, 2020.","title":"Correlation graph convolutional network for pedestrian attribute recognition","authors":"H Fan, H M Hu, S Liu, W Lu, S Pu","year":"2020","venue":"IEEE Transactions on Multimedia","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Gao et al., 2019] Lian Gao, Di Huang, Yuanfang Guo, and Yunhong Wang. Pedestrian attribute recognition via hier- archical multi-task learning and relationship attention. In Proceedings of the 27th ACM International Conference on Multimedia, MM '19, page 1340-1348, New York, NY, USA, 2019. Association for Computing Machinery.","title":"Pedestrian attribute recognition via hierarchical multi-task learning and relationship attention","authors":"Lian Gao, Di Huang, Yuanfang Guo, Yunhong Wang","year":"2019","venue":"Proceedings of the 27th ACM International Conference on Multimedia, MM '19","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Guo et al., 2020] H. Guo, K. Zheng, X. Fan, H. Yu, and S. Wang. Visual attention consistency under image transforms for multi-label image classification. In 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020.","title":"Visual attention consistency under image transforms for multi-label image classification","authors":"H Guo, K Zheng, X Fan, H Yu, S Wang","year":"2019","venue":"IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[He et al., 2016] K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. IEEE, 2016.","title":"Deep residual learning for image recognition","authors":"K He, X Zhang, S Ren, J Sun","year":"2016","venue":"IEEE","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Ji et al., 2020] Z. Ji, Z. Hu, E. He, J. Han, and Y. Pang. Pedestrian attribute recognition based on multiple time steps attention. Pattern Recognition Letters, 138(2), 2020.","title":"Pedestrian attribute recognition based on multiple time steps attention","authors":"Z Ji, Z Hu, E He, J Han, Y Pang","year":"2020","venue":"Pattern Recognition Letters","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Jia et al., 2021a] Jian Jia, Xiaotang Chen, and Kaiqi Huang. Spatial and semantic consistency regularizations for pedestrian attribute recognition. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 962-971, October 2021.","title":"Spatial and semantic consistency regularizations for pedestrian attribute recognition","authors":"Jia","year":"2021","venue":"Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Jia et al., 2021b] Jian Jia, Houjing Huang, Xiaotang Chen, and Kaiqi Huang. Rethinking of pedestrian attribute recog- nition: A reliable evaluation under zero-shot pedestrian identity setting. arXiv preprint arXiv:2107.03576, 2021.","title":"Rethinking of pedestrian attribute recognition: A reliable evaluation under zero-shot pedestrian identity setting","authors":"Jia","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Jia et al., 2022] Jian Jia, Naiyu Gao, Fei He, Xiaotang Chen, and Kaiqi Huang. Learning disentangled attribute representations for robust pedestrian attribute recognition. In Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI 2022, Thirty-Fourth Conference on Innovative Ap- plications of Artificial Intelligence, IAAI 2022, The Twel- veth Symposium on Educational Advances in Artificial In- telligence, EAAI 2022 Virtual Event, February 22 -March 1, 2022, pages 1069-1077. AAAI Press, 2022.","title":"Learning disentangled attribute representations for robust pedestrian attribute recognition","authors":"Jian Jia, Naiyu Gao, Fei He, Xiaotang Chen, Kaiqi Huang","year":"2022","venue":"Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI 2022, Thirty-Fourth Conference on Innovative Applications of Artificial Intelligence, IAAI 2022, The Twelveth Symposium on Educational Advances in Artificial Intelligence, EAAI 2022 Virtual Event","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Li et al., 2016] Dangwei Li, Zhang Zhang, Xiaotang Chen, Haibin Ling, and Kaiqi Huang. A richly annotated dataset for pedestrian attribute recognition. arXiv preprint arXiv:1603.07054, 2016.","title":"A richly annotated dataset for pedestrian attribute recognition","authors":"Dangwei Li, Zhang Zhang, Xiaotang Chen, Haibin Ling, Kaiqi Huang","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Li et al., 2017] D. Li, X. Chen, Z. Zhang, and K. Huang. Learning deep context-aware features over body and latent parts for person re-identification. IEEE, 2017.","title":"Learning deep context-aware features over body and latent parts for person re-identification","authors":"D Li, X Chen, Z Zhang, K Huang","year":"2017","venue":"IEEE","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Li et al., 2022] Wanhua Li, Zhexuan Cao, Jianjiang Feng, Jie Zhou, and Jiwen Lu. Label2label: A language mod- eling framework formulti-attribute learning. Springer, Cham, 2022.","title":"Label2label: A language modeling framework formulti-attribute learning","authors":"Wanhua Li, Zhexuan Cao, Jianjiang Feng, Jie Zhou, Jiwen Lu","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Liu et al., 2017] Xihui Liu, Haiyu Zhao, Maoqing Tian, Lu Sheng, Jing Shao, Shuai Yi, Junjie Yan, and Xiaogang Wang. Hydraplus-net: Attentive deep features for pedes- trian analysis. In Proceedings of the IEEE international conference on computer vision, pages 350-359, 2017.","title":"Hydraplus-net: Attentive deep features for pedestrian analysis","authors":"Xihui Liu, Haiyu Zhao, Maoqing Tian, Lu Sheng, Jing Shao, Shuai Yi, Junjie Yan, Xiaogang Wang","year":"2017","venue":"Proceedings of the IEEE international conference on computer vision","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Liu et al., 2018] Pengze Liu, Xihui Liu, Junjie Yan, and Jing Shao. Localization guided learning for pedestrian attribute recognition. arXiv preprint arXiv:1808.09102, 2018.","title":"Localization guided learning for pedestrian attribute recognition","authors":"Liu","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Liu et al., 2022] Zhuang Liu, Hanzi Mao, Chao-Yuan Wu, Christoph Feichtenhofer, Trevor Darrell, and Saining Xie. A convnet for the 2020s. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11976-11986, 2022.","title":"A convnet for the 2020s","authors":"Zhuang Liu, Hanzi Mao, Chao-Yuan Wu, Christoph Feichtenhofer, Trevor Darrell, Saining Xie","year":"2022","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Meng et al., 2021] Qiang Meng, Shichao Zhao, Zhida Huang, and Feng Zhou. Magface: A universal repre- sentation for face recognition and quality assessment. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 14225- 14234, June 2021.","title":"Magface: A universal representation for face recognition and quality assessment","authors":"Qiang Meng, Shichao Zhao, Zhida Huang, Feng Zhou","year":"2021","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Mikolov et al., 2013] Tomas Mikolov, Kai Chen, Greg Cor- rado, and Jeffrey Dean. Efficient estimation of word rep- resentations in vector space. Computer Science, 2013.","title":"Efficient estimation of word representations in vector space","authors":"Tomas Mikolov, Kai Chen, Greg Corrado, Jeffrey Dean","year":"2013","venue":"Computer Science","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Sarafianos and Kakadiaris, 2018] Nikolaos Sarafianos and Ioannis A. Kakadiaris. Deep imbalanced attribute classifi- cation using visual attention aggregation. In ECCV 2018, 2018.","title":"Deep imbalanced attribute classification using visual attention aggregation","authors":"Nikolaos Sarafianos, Ioannis A Kakadiaris","year":"2018","venue":"ECCV 2018","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Shalev et al., 2018] Gabi Shalev, Yossi Adi, and Joseph Keshet. Out-of-distribution detection using multiple se- mantic label representations. In Advances in Neural Infor- mation Processing Systems, pages 7375-7385, 2018.","title":"Out-of-distribution detection using multiple semantic label representations","authors":"Gabi Shalev, Yossi Adi, Joseph Keshet","year":"2018","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Specker et al., 2022] Andreas Specker, Mickael Cormier, and Jürgen Beyerer. Upar: Unified pedestrian attribute recognition and person retrieval. ArXiv, abs/2209.02522, 2022.","title":"Upar: Unified pedestrian attribute recognition and person retrieval","authors":"Andreas Specker, Mickael Cormier, Jürgen Beyerer","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Tan et al., 2020] Z. Tan, Y. Yang, J. Wan, G. Guo, and S. Z. Li. Relation-aware pedestrian attribute recognition with graph convolutional networks. Proceedings of the AAAI Conference on Artificial Intelligence, 34(7):12055-12062, 2020.","title":"Relation-aware pedestrian attribute recognition with graph convolutional networks","authors":"Z Tan, Y Yang, J Wan, G Guo, S Z Li","year":"2020","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Tang et al., 2019] C. Tang, L. Sheng, Z. X. Zhang, and X. Hu. Improving pedestrian attribute recognition with weakly-supervised multi-scale attribute-specific localiza- tion. In 2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2019.","title":"Improving pedestrian attribute recognition with weakly-supervised multi-scale attribute-specific localization","authors":"C Tang, L Sheng, Z X Zhang, X Hu","year":"2019","venue":"IEEE/CVF International Conference on Computer Vision (ICCV)","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Wang et al., 2016] J. Wang, X. Zhu, and S. Gong. Video semantic clustering with sparse and incomplete tags. In Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16), 2016.","title":"Video semantic clustering with sparse and incomplete tags","authors":"J Wang, X Zhu, S Gong","year":"2016","venue":"Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16)","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Wang et al., 2017] Jingya Wang, Xiatian Zhu, and Shao- gang Gong. Discovering visual concept structure with sparse and incomplete tags. Artificial Intelligence, 250:16-36, 2017.","title":"Discovering visual concept structure with sparse and incomplete tags","authors":"Wang","year":"2017","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Wang et al., 2018] F. Wang, J. Cheng, W. Liu, and H. Liu. Additive margin softmax for face verification. IEEE Signal Processing Letters, pages 926-930, 2018.","title":"Additive margin softmax for face verification","authors":"F Wang, J Cheng, W Liu, H Liu","year":"2018","venue":"IEEE Signal Processing Letters","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhang et al., 2017] Hongyi Zhang, Moustapha Cisse, Yann N Dauphin, and David Lopez-Paz. mixup: Be- yond empirical risk minimization. arXiv preprint arXiv:1710.09412, 2017.","title":"mixup: Beyond empirical risk minimization","authors":"Hongyi Zhang, Moustapha Cisse, David Yann N Dauphin, Lopez-Paz","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Zhou et al., 2016] Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, and Antonio Torralba. Learning deep features for discriminative localization. In Proceed- ings of the IEEE conference on computer vision and pat- tern recognition, pages 2921-2929, 2016.","title":"Learning deep features for discriminative localization","authors":"Zhou","year":"2016","venue":"Proceedings of the IEEE conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Zhou, 2022] Y. Zhou. Rethinking reconstruction autoencoder-based out-of-distribution detection. Pro- ceedings of the IEEE conference on computer vision and pattern recognition, 2022.","title":"Rethinking reconstruction autoencoder-based out-of-distribution detection","authors":"Y Zhou","year":"2022","venue":"Proceedings of the IEEE conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Zhu et al., 2017] J. Zhu, S. Liao, Z. Lei, and S. Z. Li. Multi-label convolutional neural network based pedes- trian attribute classification. Image Vision Computing, 58(FEB.):224-229, 2017.","title":"Multi-label convolutional neural network based pedestrian attribute classification","authors":"J Zhu, S Liao, Z Lei, S Z Li","year":"2017","venue":"Image Vision Computing","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}