The Effect of Data Augmentation on the Performance of Convolutional Neural Networks

Soft biometrics classification has been gaining acceptance during the recent years for critical applications, mainly in the security field. Recognizing individuals by using only behavioral, physical or psychological characteristics is a task that can be helpful for several purposes. Thus, different Deep Learning approaches have been proposed to perform this task. Since these methods require a large amount of data to avoid overfitting, data augmentation is a commonly used method. However, its isolated effect on the performance of the models are usually not evaluated. This work aims at studying the effect of different data augmentation strategies on the performances of two Convolutional Neural Network architectures for classifying soft biometrics attributes from samples of a novel dataset: LABICv1.

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

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

[3]  Bao Lien Hung,et al.  Using One-Dimensional Linear Interpolation Method to Check Over-Fitting in Neural Network with Multi-Dimensional Inputs , 2014 .

[4]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[5]  Léon Bottou,et al.  Large-Scale Machine Learning with Stochastic Gradient Descent , 2010, COMPSTAT.

[6]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[7]  Mark S. Nixon,et al.  Retrieving relative soft biometrics for semantic identification , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[8]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[9]  Sridha Sridharan,et al.  Soft-Biometrics: Unconstrained Authentication in a Surveillance Environment , 2009, 2009 Digital Image Computing: Techniques and Applications.

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

[11]  A. Ng.  Feature selection, L1 vs. L2 regularization, and rotational invariance , 2004, Twenty-first international conference on Machine learning - ICML '04.

[12]  Michael A. Arbib,et al.  The handbook of brain theory and neural networks , 1995, A Bradford book.

[13]  Mehryar Mohri,et al.  L2 Regularization for Learning Kernels , 2009, UAI.

[14]  Shengcai Liao,et al.  Multi-label CNN based pedestrian attribute learning for soft biometrics , 2015, 2015 International Conference on Biometrics (ICB).

[15]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[16]  Andrew Zisserman,et al.  Return of the Devil in the Details: Delving Deep into Convolutional Nets , 2014, BMVC.

[17]  Heitor Silvério Lopes,et al.  Extracting human attributes using a convolutional neural network approach , 2015, Pattern Recognit. Lett..