Anchored Regression Networks Applied to Age Estimation and Super Resolution

We propose the Anchored Regression Network (ARN), a nonlinear regression network which can be seamlessly integrated into various networks or can be used stand-alone when the features have already been fixed. Our ARN is a smoothed relaxation of a piecewise linear regressor through the combination of multiple linear regressors over soft assignments to anchor points. When the anchor points are fixed the optimal ARN regressors can be obtained with a closed form global solution, otherwise ARN admits end-toend learning with standard gradient based methods. We demonstrate the power of the ARN by applying it to two very diverse and challenging tasks: age prediction from face images and image super-resolution. In both cases, ARNs yield strong results.

[1]  Andrea Prati,et al.  Facial Age Estimation Through the Fusion of Texture and Local Appearance Descriptors , 2014, ECCV Workshops.

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

[3]  Josephine Sullivan,et al.  One millisecond face alignment with an ensemble of regression trees , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  David A. McAllester,et al.  Object Detection with Discriminatively Trained Part Based Models , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  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.

[6]  Guodong Guo,et al.  A framework for joint estimation of age, gender and ethnicity on a large database , 2014, Image Vis. Comput..

[7]  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).

[8]  Bodo Rosenhahn,et al.  PSyCo: Manifold Span Reduction for Super Resolution , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[10]  Lei Zhang,et al.  Joint Learning of Multiple Regressors for Single Image Super-Resolution , 2016, IEEE Signal Processing Letters.

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

[12]  Lourdes Agapito,et al.  Computer Vision - ECCV 2014 Workshops: Zurich, Switzerland, September 6-7 and 12, 2014, Proceedings, Part II , 2015 .

[13]  Tong Zhang,et al.  Improved Local Coordinate Coding using Local Tangents , 2010, ICML.

[14]  Ian D. Reid,et al.  Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Luc Van Gool,et al.  Jointly Optimized Regressors for Image Super‐resolution , 2015, Comput. Graph. Forum.

[16]  Philip H. S. Torr,et al.  Locally Linear Support Vector Machines , 2011, ICML.

[17]  Andrew Zisserman,et al.  In Search of Art , 2014, ECCV Workshops.

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

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

[20]  Helmuth Späth,et al.  Algorithm 39 Clusterwise linear regression , 1979, Computing.

[21]  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.

[22]  W. DeSarbo,et al.  A maximum likelihood methodology for clusterwise linear regression , 1988 .

[23]  Michael Elad,et al.  On Single Image Scale-Up Using Sparse-Representations , 2010, Curves and Surfaces.

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

[25]  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).

[26]  Kyoung Mu Lee,et al.  Accurate Image Super-Resolution Using Very Deep Convolutional Networks , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Guodong Guo,et al.  Simultaneous dimensionality reduction and human age estimation via kernel partial least squares regression , 2011, CVPR 2011.

[28]  Xiaoou Tang,et al.  Image Super-Resolution Using Deep Convolutional Networks , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  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).

[30]  Yihong Gong,et al.  Nonlinear Learning using Local Coordinate Coding , 2009, NIPS.

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

[32]  Xiaoou Tang,et al.  Learning a Deep Convolutional Network for Image Super-Resolution , 2014, ECCV.

[33]  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).

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

[35]  Ashutosh Saxena,et al.  Learning Depth from Single Monocular Images , 2005, NIPS.

[36]  Luc Van Gool,et al.  Seven Ways to Improve Example-Based Single Image Super Resolution , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[37]  Yihong Gong,et al.  Locality-constrained Linear Coding for image classification , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[38]  Colin Raffel,et al.  Lasagne: First release. , 2015 .

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

[40]  Zhi-Hua Zhou,et al.  Automatic Age Estimation Based on Facial Aging Patterns , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[41]  Luc Van Gool,et al.  A+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution , 2014, ACCV.

[42]  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).

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

[44]  Shaogang Gong,et al.  Cumulative Attribute Space for Age and Crowd Density Estimation , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[45]  Dit-Yan Yeung,et al.  Multi-task warped Gaussian process for personalized age estimation , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

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

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

[48]  D. Basak,et al.  Support Vector Regression , 2008 .

[49]  Thomas S. Huang,et al.  Image super-resolution as sparse representation of raw image patches , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[50]  John Salvatier,et al.  Theano: A Python framework for fast computation of mathematical expressions , 2016, ArXiv.

[51]  C. Christodoulou,et al.  Comparing different classifiers for automatic age estimation , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).