{"type":"ScholarlyArticle","title":"Biased Feature Learning for Occlusion Invariant Face Recognition","authors":[{"name":"Changbin Shao","slug":"changbin-shao","given":"Changbin","family":"Shao","affiliation":"State Key Laboratory for Novel Software Technology , Nanjing University , Nanjing , China; School of Computer , Jiangsu University of Science and Technology , Zhenjiang , China"},{"name":"Jing Huo","slug":"jing-huo","given":"Jing","family":"Huo","affiliation":"State Key Laboratory for Novel Software Technology , Nanjing University , Nanjing , China"},{"name":"Lei Qi","slug":"lei-qi","given":"Lei","family":"Qi","affiliation":"State Key Laboratory for Novel Software Technology , Nanjing University , Nanjing , China"},{"name":"Zhen-Hua Feng","slug":"zhen-hua-feng","given":"Zhen-Hua","family":"Feng","affiliation":"Department of Computer Science , and the Centre for Vision , Speech and Signal Processing , University of Surrey , Guildford , UK"},{"name":"Wenbin Li","slug":"wenbin-li","given":"Wenbin","family":"Li","affiliation":"State Key Laboratory for Novel Software Technology , Nanjing University , Nanjing , China"},{"name":"Chuanqi Dong","slug":"chuanqi-dong","given":"Chuanqi","family":"Dong","affiliation":"State Key Laboratory for Novel Software Technology , Nanjing University , Nanjing , China"},{"name":"Yang Gao","slug":"yang-gao","given":"Yang","family":"Gao","affiliation":"State Key Laboratory for Novel Software Technology , Nanjing University , Nanjing , China"}],"abstract":"To address the challenges posed by unknown occlusions, we propose a Biased Feature Learning (BFL) framework for occlusion-invariant face recognition. We first construct an extended dataset using a multi-scale data augmentation method. For model training, we modify the label loss to adjust the impact of normal and occluded samples. Further, we propose a biased guidance strategy to manipulate the optimization of a network so that the feature embedding space is dominated by non-occluded faces. BFL not only enhances the robustness of a network to unknown occlusions but also maintains or even improves its performance for normal faces. Experimental results demonstrate its superiority as well as the generalization capability with different network architectures and loss functions.","doi":"10.24963/ijcai.2020/93","url":"https://ijcai.org/proceedings/2020/93","pdf":"https://ijcai.org/proceedings/2020/0093.pdf","markdown":"https://ijcai.org/proceedings/2020/93.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/93","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Computer Vision","track":"Main track","number":93,"pages":{"first":666,"last":672},"keywords":["Computer Vision: Biometrics, Face and Gesture Recognition"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24602/file_24602.m3u8","length_sec":295,"provider":"hls"}],"references":[{"position":1,"raw":"[Candès et al., 2011] Emmanuel J Candès, Xiaodong Li, Yi Ma, and John Wright. Robust principal component analysis? Journal of the ACM, 58(3):11, 2011.","title":"Robust principal component analysis","authors":"J Emmanuel, Xiaodong Candès, Yi Li, John Ma, Wright","year":"2011","venue":"Journal of the ACM","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Deng et al., 2012] Weihong Deng, Jiani Hu, and Jun Guo. Extended src: Undersampled face recognition via intra- class variant dictionary. TPAMI, 34(9):1864-1870, 2012.","title":"Extended src: Undersampled face recognition via intraclass variant dictionary","authors":"Weihong Deng, Jiani Hu, Jun Guo","year":"2012","venue":"TPAMI","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Deng et al., 2019] Jiankang Deng, Jia Guo, Niannan Xue, and Stefanos Zafeiriou. Arcface: Additive angular mar- gin loss for deep face recognition. In CVPR, pages 4685- 4694, 2019.","title":"Arcface: Additive angular margin loss for deep face recognition","authors":"Deng","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Goodfellow et al., 2014] Ian Goodfellow, Jean Pougetabad- ie, Mehdi Mirza, Bing Xu, David Wardefarley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Generative adversarial nets. In NIPS, pages 2672-2680, 2014.","title":"Generative adversarial nets","authors":"Ian Goodfellow, Jean Pougetabadie, Mehdi Mirza, Bing Xu, David Wardefarley, Sherjil Ozair, Aaron Courville, Yoshua Bengio","year":"2014","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[He et al., 2016] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recog- nition. In CVPR, pages 770-778, 2016.","title":"Deep residual learning for image recognition","authors":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Iliadis et al., 2017] Michael Iliadis, Haohong Wang, Rafael Molina, and Aggelos K Katsaggelos. Robust and low-rank representation for fast face identification with occlusions. TIP, 26(5):2203-2218, 2017.","title":"Robust and low-rank representation for fast face identification with occlusions","authors":"Michael Iliadis, Haohong Wang, Rafael Molina, Aggelos K Katsaggelos","year":"2017","venue":"TIP","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Li et al., 2013] Xiaoxin Li, Daoqing Dai, Xiaofei Zhang, and Chuanxian Ren. Structured sparse error coding for face recognition with occlusion. TIP, 22(5):1889-1900, 2013.","title":"Structured sparse error coding for face recognition with occlusion","authors":"Xiaoxin Li, Daoqing Dai, Xiaofei Zhang, Chuanxian Ren","year":"2013","venue":"TIP","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Li et al., 2017] Yijun Li, Sifei Liu, Jimei Yang, and Mingh- suan Yang. Generative face completion. In CVPR, pages 5892-5900, 2017.","title":"Generative face completion","authors":"Yijun Li, Sifei Liu, Jimei Yang, Minghsuan Yang","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Liu et al., 2013] Guangcan Liu, Zhouchen Lin, Shuicheng Yan, Ju Sun, Yong Yu, and Yi Ma. Robust recovery of subspace structures by low-rank representation. TPAMI, 35(1):171-184, 2013.","title":"Robust recovery of subspace structures by low-rank representation","authors":"Liu","year":"2013","venue":"TPAMI","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Loshchilov and Hutter, 2019] Ilya Loshchilov and Frank Hutter. Decoupled weight decay regularization. In ICLR, 2019.","title":"Ilya Loshchilov and Frank Hutter. Decoupled weight decay regularization","authors":"Hutter Loshchilov","year":"2019","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Ou et al., 2018] Weihua Ou, Xiao Luan, Jianping Gou, Quan Zhou, Wenjun Xiao, Xiangguang Xiong, and Wu Zeng. Robust discriminative nonnegative dictionary learning for occluded face recognition. Pattern Recogni- tion Letters, 107:41-49, 2018.","title":"Robust discriminative nonnegative dictionary learning for occluded face recognition","authors":"Weihua Ou, Xiao Luan, Jianping Gou, Quan Zhou, Wenjun Xiao, Xiangguang Xiong, Wu Zeng","year":"2018","venue":"Pattern Recognition Letters","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Saeztrigueros et al., 2018] Daniel Saeztrigueros, Li Meng, and Margaret Hartnett. Enhancing convolutional neural networks for face recognition with occlusion maps and batch triplet loss. Image and Vision Computing, 79:99- 108, 2018.","title":"Enhancing convolutional neural networks for face recognition with occlusion maps and batch triplet loss","authors":"Daniel Saeztrigueros, Li Meng, Margaret Hartnett","year":"2018","venue":"Image and Vision Computing","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Schroff et al., 2015] Florian Schroff, Dmitry Kalenichenko, and James Philbin. Facenet: A unified embedding for face recognition and clustering. In CVPR, pages 815-823, 2015.","title":"Facenet: A unified embedding for face recognition and clustering","authors":"Schroff","year":"2015","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Shao et al., 2017] Changbin Shao, Xiaoning Song, Zhenhua Feng, Xiaojun Wu, and Yuhui Zheng. Dynamic dictionary optimization for sparse-representation-based face classi- fication using local difference images. Information Sci- ences, 393:1-14, 2017.","title":"Dynamic dictionary optimization for sparse-representation-based face classification using local difference images","authors":"Shao","year":"2017","venue":"Information Sciences","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Singh et al., 2019] Maneet Singh, Richa Singh, Mayank Vatsa, Nalini K Ratha, and Rama Chellappa. Recognizing disguised faces in the wild. TBIOM, 1(2):97-108, 2019.","title":"Recognizing disguised faces in the wild","authors":"Maneet Singh, Richa Singh, Mayank Vatsa, Rama Nalini K Ratha, Chellappa","year":"2019","venue":"TBIOM","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Song et al., 2019] Lingxue Song, Dihong Gong, Zhifeng Li, Changsong Liu, and Wei Liu. Occlusion robust face recog- nition based on mask learning with pairwise differential siamese network. In ICCV, pages 773-782, 2019.","title":"Occlusion robust face recognition based on mask learning with pairwise differential siamese network","authors":"Song","year":"2019","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Taigman et al., 2014] Yaniv Taigman, Ming Yang, Marcau- relio Ranzato, and Lior Wolf. Deepface: Closing the gap to human-level performance in face verification. In CVPR, pages 1701-1708, 2014.","title":"Deepface: Closing the gap to human-level performance in face verification","authors":"Yaniv Taigman, Ming Yang, Marcaurelio Ranzato, Lior Wolf","year":"2014","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Wang et al., 2018] Hao Wang, Yitong Wang, Zheng Zhou, Xing Ji, Dihong Gong, Jingchao Zhou, Zhifeng Li, and Wei Liu. Cosface: Large margin cosine loss for deep face recognition. In CVPR, pages 5265-5274, 2018.","title":"Cosface: Large margin cosine loss for deep face recognition","authors":"Hao Wang, Yitong Wang, Zheng Zhou, Xing Ji, Dihong Gong, Jingchao Zhou, Zhifeng Li, Wei Liu","year":"2018","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Wen et al., 2016] Yandong Wen, Kaipeng Zhang, Zhifeng Li, and Yu Qiao. A discriminative feature learning ap- proach for deep face recognition. In ECCV, pages 499- 515. Springer, 2016.","title":"A discriminative feature learning approach for deep face recognition","authors":"Yandong Wen, Kaipeng Zhang, Zhifeng Li, Yu Qiao","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Wright et al., 2009a] John Wright, Arvind Ganesh, Shankar R Rao, Yigang Peng, and Yi Ma. Robust prin- cipal component analysis: Exact recovery of corrupted low-rank matrices via convex optimization. In NIPS, pages 2080-2088, 2009.","title":"Robust principal component analysis: Exact recovery of corrupted low-rank matrices via convex optimization","authors":"Wright","year":"2009","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Wright et al., 2009b] John Wright, Allen Y Yang, Arvind Ganesh, Shankar Sastry, and Yi Ma. Robust face recog- nition via sparse representation. TPAMI, 31(2):210-227, 2009.","title":"Robust face recognition via sparse representation","authors":"Wright","year":"2009","venue":"TPAMI","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Wu and Ding, 2018] Choying Wu and Jianjiun Ding. Oc- cluded face recognition using low-rank regression with generalized gradient direction. Pattern Recognition, 80:256-268, 2018.","title":"Occluded face recognition using low-rank regression with generalized gradient direction","authors":"Ding Wu, Choying Wu, Jianjiun Ding","year":"2018","venue":"Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wu et al., 2018] Xiang Wu, Ran He, Zhenan Sun, and Tie- niu Tan. A light cnn for deep face representation with noisy labels. TIFS, 13(11):2884-2896, 2018.","title":"A light cnn for deep face representation with noisy labels","authors":"Xiang Wu, Ran He, Zhenan Sun, Tieniu Tan","year":"2018","venue":"TIFS","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Yang et al., 2017] Jian Yang, Lei Luo, Jianjun Qian, Ying Tai, Fanlong Zhang, and Yong Xu. Nuclear norm based matrix regression with applications to face recog- nition with occlusion and illumination changes. TPAMI, 39(1):156-171, 2017.","title":"Nuclear norm based matrix regression with applications to face recognition with occlusion and illumination changes","authors":"Jian Yang, Lei Luo, Jianjun Qian, Ying Tai, Fanlong Zhang, Yong Xu","year":"2017","venue":"TPAMI","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Yuan and Park, 2019] Xiaowei Yuan and Inkyu Park. Face de-occlusion using 3d morphable model and generative adversarial network. In ICCV, pages 10062-10071, 2019.","title":"Face de-occlusion using 3d morphable model and generative adversarial network","authors":"Xiaowei Yuan, Inkyu Park","year":"2019","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zhang et al., 2015] Fanlong Zhang, Jian Yang, Ying Tai, and Jinhui Tang. Double nuclear norm-based matrix de- composition for occluded image recovery and background modeling. TIP, 24(6):1956-1966, 2015.","title":"Double nuclear norm-based matrix decomposition for occluded image recovery and background modeling","authors":"Fanlong Zhang, Jian Yang, Ying Tai, Jinhui Tang","year":"2015","venue":"TIP","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Zhao et al., 2017] Fang Zhao, Jiashi Feng, Jian Zhao, Wen- han Yang, and Shuicheng Yan. Robust lstm-autoencoders for face de-occlusion in the wild. TIP, 27(2):778-790, 2017.","title":"Robust lstm-autoencoders for face de-occlusion in the wild","authors":"Fang Zhao, Jiashi Feng, Jian Zhao, Wenhan Yang, Shuicheng Yan","year":"2017","venue":"TIP","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}