CNN-Based Age Classification via Transfer Learning

Age estimation has always hit people’s eyes. While most previous works have focused on constrained images taken under lab condition, which is far from real-world age estimation. The benchmark we used in this paper is the unconstrained Adience [3], which is believed to better reflect the traits of age in the wild condition. In this paper, we adapted contrastive loss to fine-tune the pre-trained VGG-16 over FG-NET to get a better start point and proposed AvgOut-FC Layer to enhance the performance of the models over Audience. We have achieved better results over the Adience benchmark than previous works, which demonstrated the effectiveness of our methods.

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

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

[3]  Tal Hassner,et al.  Age and Gender Estimation of Unfiltered Faces , 2014, IEEE Transactions on Information Forensics and Security.

[4]  Yann LeCun,et al.  Learning a similarity metric discriminatively, with application to face verification , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

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

[6]  Ivan Laptev,et al.  Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Yoshua Bengio,et al.  How transferable are features in deep neural networks? , 2014, NIPS.

[8]  Christian Szegedy,et al.  DeepPose: Human Pose Estimation via Deep Neural Networks , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

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

[10]  Xiaogang Wang,et al.  Hierarchical face parsing via deep learning , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Hazim Kemal Ekenel,et al.  How Transferable Are CNN-Based Features for Age and Gender Classification? , 2016, 2016 International Conference of the Biometrics Special Interest Group (BIOSIG).

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

[13]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[14]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[15]  Yoshua Bengio,et al.  Maxout Networks , 2013, ICML.