Age and gender recognition in the wild with deep attention

A novel feedforward attention mechanism for CNNs is proposed.The mechanism increases CNNs robustness to image deformations and clutter.The proposed mechanism increases CNNs performance for age and gender recognition. Face analysis in images in the wild still pose a challenge for automatic age and gender recognition tasks, mainly due to their high variability in resolution, deformation, and occlusion. Although the performance has highly increased thanks to Convolutional Neural Networks (CNNs), it is still far from optimal when compared to other image recognition tasks, mainly because of the high sensitiveness of CNNs to facial variations. In this paper, inspired by biology and the recent success of attention mechanisms on visual question answering and fine-grained recognition, we propose a novel feedforward attention mechanism that is able to discover the most informative and reliable parts of a given face for improving age and gender classification. In particular, given a downsampled facial image, the proposed model is trained based on a novel end-to-end learning framework to extract the most discriminative patches from the original high-resolution image. Experimental validation on the standard Adience, Images of Groups, and MORPH II benchmarks show that including attention mechanisms enhances the performance of CNNs in terms of robustness and accuracy.

[1]  Javier Lorenzo-Navarro,et al.  On using periocular biometric for gender classification in the wild , 2016, Pattern Recognit. Lett..

[2]  Jürgen Schmidhuber,et al.  Multi-column deep neural networks for image classification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Ming Yang,et al.  DeepFace: Closing the Gap to Human-Level Performance in Face Verification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Maher Awad,et al.  Age and gender recognition using informative features of various types , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[5]  Yun Fu,et al.  Image-Based Human Age Estimation by Manifold Learning and Locally Adjusted Robust Regression , 2008, IEEE Transactions on Image Processing.

[6]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[7]  Lalit M. Patnaik,et al.  Template based Mole Detection for Face Recognition , 2010 .

[8]  Phil Blunsom,et al.  Teaching Machines to Read and Comprehend , 2015, NIPS.

[9]  Luc Van Gool,et al.  Deep Expectation of Real and Apparent Age from a Single Image Without Facial Landmarks , 2016, International Journal of Computer Vision.

[10]  Guodong Guo,et al.  Joint estimation of age, gender and ethnicity: CCA vs. PLS , 2013, 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG).

[11]  Geoffrey E. Hinton,et al.  Learning to combine foveal glimpses with a third-order Boltzmann machine , 2010, NIPS.

[12]  Age , 2000, BMJ : British Medical Journal.

[13]  Yu Qiao,et al.  Gender and Smile Classification Using Deep Convolutional Neural Networks , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[14]  Kate Saenko,et al.  Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering , 2015, ECCV.

[15]  Misha Denil,et al.  Learning Where to Attend with Deep Architectures for Image Tracking , 2011, Neural Computation.

[16]  Arun Ross,et al.  What Else Does Your Biometric Data Reveal? A Survey on Soft Biometrics , 2016, IEEE Transactions on Information Forensics and Security.

[17]  Abdenour Hadid,et al.  Facial age estimation and gender classification using multi level local phase quantization , 2015, 2015 3rd International Conference on Control, Engineering & Information Technology (CEIT).

[18]  Anwar M. Mirza,et al.  Gender recognition from face images with local WLD descriptor , 2012, 2012 19th International Conference on Systems, Signals and Image Processing (IWSSIP).

[19]  Anil K. Jain,et al.  Age estimation from face images: Human vs. machine performance , 2013, 2013 International Conference on Biometrics (ICB).

[20]  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).

[21]  Antonio Torralba,et al.  Contextual guidance of eye movements and attention in real-world scenes: the role of global features in object search. , 2006, Psychological review.

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

[23]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[24]  Marwan Mattar,et al.  Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments , 2008 .

[25]  Alexander J. Smola,et al.  Stacked Attention Networks for Image Question Answering , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Li-Jia Li,et al.  Multi-view Face Detection Using Deep Convolutional Neural Networks , 2015, ICMR.

[27]  Norah Jones,et al.  E-Learning: A Fresh Look , 2006 .

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

[29]  Daniel González-Jiménez,et al.  Single- and cross- database benchmarks for gender classification under unconstrained settings , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

[30]  Mahir Faik Karaaba,et al.  Deep Convolutional Neural Networks and Support Vector Machines for Gender Recognition , 2015, 2015 IEEE Symposium Series on Computational Intelligence.

[31]  Andrew Zisserman,et al.  Spatial Transformer Networks , 2015, NIPS.

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

[33]  Carlos Segura,et al.  A deep analysis on age estimation , 2015, Pattern Recognit. Lett..

[34]  Domingo Mery,et al.  Recognition of Facial Attributes Using Adaptive Sparse Representations of Random Patches , 2014, ECCV Workshops.

[35]  Theo Gevers,et al.  Learning-based encoding with soft assignment for age estimation under unconstrained imaging conditions , 2012, Image Vis. Comput..

[36]  Terrence J. Sejnowski,et al.  SEXNET: A Neural Network Identifies Sex From Human Faces , 1990, NIPS.

[37]  Matti Pietikäinen,et al.  Age Classification in Unconstrained Conditions Using LBP Variants , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[38]  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).

[39]  Xiaogang Wang,et al.  Deep Learning Face Representation by Joint Identification-Verification , 2014, NIPS.

[40]  Wei Zhang,et al.  Deeply Learned Rich Coding for Cross-Dataset Facial Age Estimation , 2015, 2015 IEEE International Conference on Computer Vision Workshop (ICCVW).

[41]  Haroon Idrees,et al.  Tracking in dense crowds using prominence and neighborhood motion concurrence , 2014, Image Vis. Comput..

[42]  Caifeng Shan.  Learning local features for age estimation on real-life faces , 2010, MPVA '10.

[43]  Ming Yang,et al.  3D Convolutional Neural Networks for Human Action Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[44]  Andrew C. Gallagher,et al.  Understanding images of groups of people , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[45]  Rama Chellappa,et al.  A cascaded convolutional neural network for age estimation of unconstrained faces , 2016, 2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems (BTAS).

[46]  Christof Koch,et al.  A Model of Saliency-Based Visual Attention for Rapid Scene Analysis , 2009 .

[47]  Anil K. Jain,et al.  Unconstrained Face Recognition: Identifying a Person of Interest From a Media Collection , 2014, IEEE Transactions on Information Forensics and Security.

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

[49]  Xin Liu,et al.  AgeNet: Deeply Learned Regressor and Classifier for Robust Apparent Age Estimation , 2015, 2015 IEEE International Conference on Computer Vision Workshop (ICCVW).

[50]  Claudio A. Perez,et al.  Gender Classification Based on Fusion of Different Spatial Scale Features Selected by Mutual Information From Histogram of LBP, Intensity, and Shape , 2013, IEEE Transactions on Information Forensics and Security.

[51]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[52]  Luc Van Gool,et al.  DEX: Deep EXpectation of Apparent Age from a Single Image , 2015, 2015 IEEE International Conference on Computer Vision Workshop (ICCVW).

[53]  Yoshua Bengio,et al.  Show, Attend and Tell: Neural Image Caption Generation with Visual Attention , 2015, ICML.

[54]  Alex Graves,et al.  Recurrent Models of Visual Attention , 2014, NIPS.

[55]  Sergio Escalera,et al.  ChaLearn Looking at People 2015: Apparent Age and Cultural Event Recognition Datasets and Results , 2015, 2015 IEEE International Conference on Computer Vision Workshop (ICCVW).

[56]  Hiroshi Nagahashi,et al.  Classification of Age Group Based on Facial Images of Young Males by Using Neural Networks , 2001 .

[57]  Andrew Zisserman,et al.  Deep Face Recognition , 2015, BMVC.

[58]  Javier Lorenzo-Navarro,et al.  Descriptors and regions of interest fusion for in- and cross-database gender classification in the wild , 2017, Image Vis. Comput..

[59]  Maja Pantic,et al.  Hierarchical On-line Appearance-Based Tracking for 3D head pose, eyebrows, lips, eyelids and irises , 2013, Image Vis. Comput..

[60]  Yuan Dong,et al.  Automatic age estimation based on deep learning algorithm , 2016, Neurocomputing.

[61]  Changsheng Li,et al.  Learning ordinal discriminative features for age estimation , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

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

[63]  Yun Fu,et al.  A study on automatic age estimation using a large database , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[64]  Niels da Vitoria Lobo,et al.  Age classification from facial images , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[65]  Roberto Paredes,et al.  Local Deep Neural Networks for gender recognition , 2016, Pattern Recognit. Lett..

[66]  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).

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

[68]  Yi-Ping Hung,et al.  Ordinal hyperplanes ranker with cost sensitivities for age estimation , 2011, CVPR 2011.

[69]  L M Patnaik,et al.  Feature Extraction based Face Recognition , Gender and Age Classification , 2010 .

[70]  Maja Pantic,et al.  Corrigendum to "Hierarchical On-line Appearance-Based Tracking for 3D Head Pose, Eyebrows, Lips, Eyelids and Irises" [Image Vision Comput. (2013) 322-340] , 2014, Image Vis. Comput..

[71]  Caifeng Shan,et al.  Learning local binary patterns for gender classification on real-world face images , 2012, Pattern Recognit. Lett..

[72]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.