{"type":"ScholarlyArticle","title":"Age Estimation Using Expectation of Label Distribution Learning","authors":[{"name":"Bin-Bin Gao","slug":"bin-bin-gao","given":"Bin-Bin","family":"Gao","affiliation":"National Key Laboratory for Novel Software Technology , Nanjing University , China"},{"name":"Hong-Yu Zhou","slug":"hong-yu-zhou","given":"Hong-Yu","family":"Zhou","affiliation":"National Key Laboratory for Novel Software Technology , Nanjing University , China"},{"name":"Jianxin Wu","slug":"jianxin-wu","given":"Jianxin","family":"Wu","affiliation":"National Key Laboratory for Novel Software Technology , Nanjing University , China"},{"name":"Xin Geng","slug":"xin-geng","given":"Xin","family":"Geng","affiliation":"MOE Key Laboratory of Computer Network and Information Integration , Southeast University , China"}],"abstract":"Age estimation performance has been greatly improved by using convolutional neural network. However, existing methods have an inconsistency between the training objectives and evaluation metric, so they may be suboptimal. In addition, these methods always adopt image classification or face recognition models with a large amount of parameters, which bring expensive computation cost and storage overhead. To alleviate these issues, we design a lightweight network architecture and propose a unified framework which can jointly learn age distribution and regress age. The effectiveness of our approach has been demonstrated on apparent and real age estimation tasks. Our method achieves new state-of-the-art results using the single model with 36$\\times$ fewer parameters and 2.6$\\times$ reduction in inference time. Moreover, our method can achieve comparable results as the state-of-the-art even though model parameters are further reduced to 0.9M~(3.8MB disk storage). We also analyze that Ranking methods are implicitly learning label distributions.","doi":"10.24963/ijcai.2018/99","url":"https://ijcai.org/proceedings/2018/99","pdf":"https://ijcai.org/proceedings/2018/0099.pdf","markdown":"https://ijcai.org/proceedings/2018/99.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/99","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Computer Vision","track":"Main track","number":99,"pages":{"first":712,"last":718},"keywords":["Computer Vision: Computer Vision","Computer Vision: Biometrics, Face and Gesture Recognition","Computer Vision: Statistical Methods and Machine Learning"],"videos":[],"references":[{"position":1,"raw":"[Antipov et al., 2016] Grigory Antipov, Moez Baccouche, Sid-Ahmed Berrani, and Jean-Luc Dugelay. Apparent age estimation from face images combining general and children-specialized deep learning models. In CVPRW, pages 96-104, 2016.","title":"Apparent age estimation from face images combining general and children-specialized deep learning models","authors":"Grigory Antipov, Moez Baccouche, Sid-Ahmed Berrani, Jean-Luc Dugelay","year":"2016","venue":"CVPRW","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Antipov et al., 2017] Grigory Antipov, Moez Baccouche, Sid-Ahmed Berrani, and Jean-Luc Dugelay. Effective train- ing of convolutional neural networks for face-based gender and age prediction. Pattern Recognition, 72:15-26, 2017.","title":"Effective training of convolutional neural networks for face-based gender and age prediction","authors":"Grigory Antipov, Moez Baccouche, Sid-Ahmed Berrani, Jean-Luc Dugelay","year":"2017","venue":"Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chang et al., 2011] Kuang-Yu Chang, Chu-Song Chen, and Yi-Ping Hung. Ordinal hyperplanes ranker with cost sen- sitivities for age estimation. In CVPR, pages 585-592, 2011.","title":"Ordinal hyperplanes ranker with cost sensitivities for age estimation","authors":"Kuang-Yu Chang, Chu-Song Chen, Yi-Ping Hung","year":"2011","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen et al., 2013] Ke Chen, S. Gong, Tao Xiang, and Chen Change Loy. Cumulative attribute space for age and crowd density estimation. In CVPR, pages 2467-2474, 2013.","title":"Cumulative attribute space for age and crowd density estimation","authors":"S Ke Chen, Tao Gong, Chen Change Xiang, Loy","year":"2013","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chen et al., 2017] Shixing Chen, Caojin Zhang, Ming Dong, Jialiang Le, and Mike Rao. Using Ranking-CNN for age estimation. In CVPR, pages 5183-5192, 2017.","title":"Using Ranking-CNN for age estimation","authors":"Shixing Chen, Caojin Zhang, Ming Dong, Jialiang Le, Mike Rao","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Cootes et al., 2001] Timothy F. Cootes, Gareth J. Edwards, and Christopher J. Taylor. Active appearance models. IEEE TPAMI, 23(6):681-685, 2001.","title":"Active appearance models","authors":"Timothy F Cootes, J Gareth, Christopher J Edwards, Taylor","year":"2001","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Escalera et al., 2015] Sergio Escalera, Junior Fabian, Pablo Pardo, Xavier Baró, Jordi Gonzalez, Hugo J Escalante, Du- san Misevic, Ulrich Steiner, and Isabelle Guyon. Chalearn looking at people 2015: Apparent age and cultural event recognition datasets and results. In ICCVW, pages 243-251, 2015.","title":"Chalearn looking at people 2015: Apparent age and cultural event recognition datasets and results","authors":"Sergio Escalera, Junior Fabian, Pablo Pardo, Xavier Baró, Jordi Gonzalez, Hugo J Escalante, Dusan Misevic, Ulrich Steiner, Isabelle Guyon","year":"2015","venue":"ICCVW","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Escalera et al., 2016] Sergio Escalera, Mercedes Torres Tor- res, Brais Martinez, Xavier Baró, Hugo Jair Escalante, Is- abelle Guyon, Georgios Tzimiropoulos, Ciprian Corneou, Marc Oliu, Mohammad Ali Bagheri, and Michel Valstar. Chalearn looking at people and faces of the world: Face analysis workshop and challenge 2016. In CVPRW, pages 706-713, 2016.","title":"Chalearn looking at people and faces of the world: Face analysis workshop and challenge","authors":"Sergio Escalera, Mercedes Torres Torres, Brais Martinez, Xavier Baró, Hugo Jair Escalante, Isabelle Guyon, Georgios Tzimiropoulos, Ciprian Corneou, Marc Oliu, Mohammad Ali Bagheri, Michel Valstar","year":"2016","venue":"CVPRW","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Gao et al., 2017] Bin-Bin Gao, Chao Xing, Chen-Wei Xie, Jianxin Wu, and Xin Geng. Deep label distribution learning with label ambiguity. IEEE TIP, 26(6):2825-2838, 2017.","title":"Deep label distribution learning with label ambiguity","authors":"Gao","year":"2017","venue":"IEEE TIP","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Geng et al., 2013] Xin Geng, Chao Yin, and Zhi-Hua Zhou. Facial age estimation by learning from label distributions. IEEE TPAMI, 35(10):2401-2412, 2013.","title":"Facial age estimation by learning from label distributions","authors":"Xin Geng, Zhi-Hua Chao Yin, Zhou","year":"2013","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Geng, 2016] Xin Geng. Label distribution learning. IEEE TKDE, 28(7):1734-1748, 2016.","title":"Label distribution learning","authors":"Xin Geng","year":"2016","venue":"IEEE TKDE","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Guo et al., 2009] Guodong Guo, Guowang Mu, Yun Fu, and Thomas S Huang. Human age estimation using bio-inspired features. In CVPR, pages 112-119, 2009.","title":"Human age estimation using bio-inspired features","authors":"Guodong Guo, Guowang Mu, Yun Fu, Thomas S Huang","year":"2009","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Guo et al., 2016] Yandong Guo, Lei Zhang, Yuxiao Hu, Xi- aodong He, and Jianfeng Gao. MS-Celeb-1M: a dataset and benchmark for large-scale face recognition. In ECCV, pages 87-102, 2016.","title":"MS-Celeb-1M: a dataset and benchmark for large-scale face recognition","authors":"Yandong Guo, Lei Zhang, Yuxiao Hu, Xiaodong He, Jianfeng Gao","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Han et al., 2015] Hu Han, Charles Otto, Xiaoming Liu, and Anil K Jain. Demographic estimation from face im- ages: Human vs. machine performance. IEEE TPAMI, 37(6):1148-1161, 2015.","title":"Demographic estimation from face images: Human vs. machine performance","authors":"Charles Hu Han, Xiaoming Otto, Anil K Liu, Jain","year":"2015","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[He et al., 2017] Zhouzhou He, Xi Li, Zhongfei Zhang, Fei Wu, Xin Geng, Yaqing Zhang, Ming-Hsuan Yang, and Yueting Zhuang. Data-dependent label distribution learning for age estimation. IEEE TIP, 26(8):3846-3858, 2017.","title":"Data-dependent label distribution learning for age estimation","authors":"He","year":"2017","venue":"IEEE TIP","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Huang et al., 2017] Dong Huang, Longfei Han, and Fer- nando De la Torre. Soft-Margin mixture of regressions. In CVPR, pages 6532-6540, 2017.","title":"Soft-Margin mixture of regressions","authors":"Dong Huang, Longfei Han, Fernando De La, Torre","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Ioffe and Szegedy, 2015] Sergey Ioffe and Christian Szegedy. Batch Normalization: accelerating deep network training by reducing internal covariate shift. In ICML, pages 448-456, 2015.","title":"Batch Normalization: accelerating deep network training by reducing internal covariate shift","authors":"Szegedy Ioffe, Sergey Ioffe, Christian Szegedy","year":"2015","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Kingma and Ba, 2015] Diederik Kingma and Jimmy Ba. Adam: A method for stochastic optimization. In ICLR, 2015.","title":"Adam: A method for stochastic optimization","authors":"Diederik Kingma, Jimmy Ba","year":"2015","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Luo et al., 2017] Jian-Hao Luo, Jianxin Wu, and Weiyao Lin. ThiNet: a filter level pruning method for deep neural net- work compression. In ICCV, pages 5058-5066, 2017.","title":"ThiNet: a filter level pruning method for deep neural network compression","authors":"Jian-Hao Luo, Jianxin Wu, Weiyao Lin","year":"2017","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Niu et al., 2016] Zhenxing Niu, Mo Zhou, Le Wang, Xinbo Gao, and Gang Hua. Ordinal regression with multiple output CNN for age estimation. In CVPR, pages 4920- 4928, 2016.","title":"Ordinal regression with multiple output CNN for age estimation","authors":"Zhenxing Niu, Mo Zhou, Le Wang, Xinbo Gao, Gang Hua","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Ranjan et al., 2017] Rajeev Ranjan, Swami Sankara- narayanan, Carlos D Castillo, and Rama Chellappa. An all-in-one convolutional neural network for face analysis. In FG, pages 17-24, 2017.","title":"An all-in-one convolutional neural network for face analysis","authors":"Rajeev Ranjan, Swami Sankaranarayanan, Carlos D Castillo, Rama Chellappa","year":"2017","venue":"FG","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Ren and Geng, 2017] Yi Ren and Xin Geng. Sense beauty by label distribution learning. In IJCAI, pages 2648-2654, 2017.","title":"Sense beauty by label distribution learning","authors":"Yi Ren, Xin Geng","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/369"},{"position":23,"raw":"[Ricanek and Tesafaye, 2006] Karl Ricanek and Tamirat Tesafaye. Morph: a longitudinal image database of normal adult age-progression. In FG, pages 341-345, 2006.","title":"Karl Ricanek and Tamirat Tesafaye. Morph: a longitudinal image database of normal adult age-progression","authors":"Tesafaye Ricanek","year":"2006","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Rothe et al., 2018] Rasmus Rothe, Radu Timofte, and Luc Van Gool. Deep expectation of real and apparent age from a single image without facial landmarks. IJCV, 126(2):144-157, 2018.","title":"Deep expectation of real and apparent age from a single image without facial landmarks","authors":"Radu Rasmus Rothe, Luc Timofte, Van Gool","year":"2018","venue":"IJCV","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Shen et al., 2017] Wei Shen, Kai Zhao, Yilu Guo, and Alan Yuille. Label distribution learning forests. In NIPS, pages 834-843, 2017.","title":"Label distribution learning forests","authors":"Wei Shen, Kai Zhao, Yilu Guo, Alan Yuille","year":"2017","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Simonyan and Zisserman, 2015] Karen Simonyan and An- drew Zisserman. Very deep convolutional networks for large-scale image recognition. In ICLR, 2015.","title":"Very deep convolutional networks for large-scale image recognition","authors":"Karen Simonyan, Andrew Zisserman","year":"2015","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Xing et al., 2016] Chao Xing, Xin Geng, and Hui Xue. Lo- gistic boosting regression for label distribution learning. In CVPR, pages 4489-4497, 2016.","title":"Logistic boosting regression for label distribution learning","authors":"Chao Xing, Xin Geng, Hui Xue","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Xu and Zhou, 2017] Miao Xu and Zhi-Hua Zhou. Incom- plete label distribution learning. In IJCAI, pages 3175- 3181, 2017.","title":"Incomplete label distribution learning","authors":"Miao Xu, Zhi-Hua Zhou","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/443"},{"position":29,"raw":"[Yi et al., 2014] Dong Yi, Zhen Lei, and Stan Z Li. Age estimation by multi-scale convolutional network. In ACCV, pages 144-158, 2014.","title":"Age estimation by multi-scale convolutional network","authors":"Dong Yi, Zhen Lei, Stan Z Li","year":"2014","venue":"ACCV","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Zhang et al., 2016] Kaipeng Zhang, Zhanpeng Zhang, Zhifeng Li, and Yu Qiao. Joint face detection and alignment using multi-task cascaded convolutional networks. IEEE SPL, 23(10):1499-1503, 2016.","title":"Joint face detection and alignment using multi-task cascaded convolutional networks","authors":"Zhang","year":"2016","venue":"IEEE SPL","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}