C3AE: Exploring the Limits of Compact Model for Age Estimation

Age estimation is a classic learning problem in computer vision. Many larger and deeper CNNs have been proposed with promising performance, such as AlexNet, VggNet, GoogLeNet and ResNet. However, these models are not practical for the embedded/mobile devices. Recently, MobileNets and ShuffleNets have been proposed to reduce the number of parameters, yielding lightweight models. However, their representation has been weakened because of the adoption of depth-wise separable convolution. In this work, we investigate the limits of compact model for small-scale image and propose an extremely Compact yet efficient Cascade Context-based Age Estimation model(C3AE). This model possesses only 1/9 and 1/2000 parameters compared with MobileNets/ShuffleNets and VggNet, while achieves competitive performance. In particular, we re-define age estimation problem by two-points representation, which is implemented by a cascade model. Moreover, to fully utilize the facial context information, multi-branch CNN network is proposed to aggregate multi-scale context. Experiments are carried out on three age estimation datasets. The state-of-the-art performance on compact model has been achieved with a relatively large margin.

[1]  Shiguang Shan,et al.  Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Xiangyu Zhang,et al.  ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design , 2018, ECCV.

[5]  Xiaolong Wang,et al.  Deeply-Learned Feature for Age Estimation , 2015, 2015 IEEE Winter Conference on Applications of Computer Vision.

[6]  Tal Hassner,et al.  Age and gender classification using convolutional neural networks , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[7]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Ching Y. Suen,et al.  Contourlet appearance model for facial age estimation , 2011, 2011 International Joint Conference on Biometrics (IJCB).

[9]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Luc Van Gool,et al.  Some Like It Hot — Visual Guidance for Preference Prediction , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  E. Hutchins.  Cognition in the wild , 1995 .

[12]  James Zijun Wang,et al.  Facial Aging and Rejuvenation by Conditional Multi-Adversarial Autoencoder with Ordinal Regression , 2018, ArXiv.

[13]  Jianxin Wu,et al.  Deep Label Distribution Learning With Label Ambiguity , 2016, IEEE Transactions on Image Processing.

[14]  Li Liu,et al.  Quantifying Facial Age by Posterior of Age Comparisons , 2017, BMVC.

[15]  Stan Z. Li,et al.  Age Estimation by Multi-scale Convolutional Network , 2014, ACCV.

[16]  Iasonas Kokkinos,et al.  DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Yi Yang,et al.  Random Erasing Data Augmentation , 2017, AAAI.

[19]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[20]  Luc Van Gool,et al.  Some Like It Hot — Visual Guidance for Preference Prediction , 2016, CVPR 2016.

[21]  Xiangyu Zhang,et al.  ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[22]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[23]  Forrest N. Iandola,et al.  SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size , 2016, ArXiv.

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

[25]  Ming Dong,et al.  Using Ranking-CNN for Age Estimation , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Jiwen Lu,et al.  Ordinal Deep Feature Learning for Facial Age Estimation , 2017, 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017).

[27]  Luc Van Gool,et al.  Deep Expectation of Real and Apparent Age from a Single Image Without Facial Landmarks , 2018, International Journal of Computer Vision.

[28]  Xiaoming Liu,et al.  Demographic Estimation from Face Images: Human vs. Machine Performance , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  Ching Y. Suen,et al.  Age estimation using Active Appearance Models and Support Vector Machine regression , 2009, 2009 IEEE 3rd International Conference on Biometrics: Theory, Applications, and Systems.

[30]  Xin Geng,et al.  Label Distribution Learning , 2013, 2013 IEEE 13th International Conference on Data Mining Workshops.

[31]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  Jiebo Luo,et al.  Human Facial Age Estimation by Cost-Sensitive Label Ranking and Trace Norm Regularization , 2017, IEEE Transactions on Multimedia.

[33]  Pi-Cheng Hsiu,et al.  SSR-Net: A Compact Soft Stagewise Regression Network for Age Estimation , 2018, IJCAI.

[34]  Gang Hua,et al.  Ordinal Regression with Multiple Output CNN for Age Estimation , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[35]  Yun Fu,et al.  Age Synthesis and Estimation via Faces: A Survey , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[36]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[37]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[38]  Mark Sandler,et al.  MobileNetV2: Inverted Residuals and Linear Bottlenecks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

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

[40]  Karl Ricanek,et al.  MORPH: a longitudinal image database of normal adult age-progression , 2006, 7th International Conference on Automatic Face and Gesture Recognition (FGR06).

[41]  Shiguang Shan,et al.  Mean-Variance Loss for Deep Age Estimation from a Face , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[42]  Stéphane Mallat,et al.  Rigid-Motion Scattering for Texture Classification , 2014, ArXiv.

[43]  Luc Van Gool,et al.  Anchored Regression Networks Applied to Age Estimation and Super Resolution , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[44]  Gang Sun,et al.  Squeeze-and-Excitation Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.