Image Classification Based on the Boost Convolutional Neural Network

Convolutional neural networks (CNNs), which are composed of multiple processing layers to learn the representations of data with multiple abstract levels, are the most successful machine learning models in recent years. However, these models can have millions of parameters and many layers, which are difficult to train, and sometimes several days or weeks are required to tune the parameters. Within this paper, we present the usage of a trained deep convolutional neural network model to extract the features of the images, and then, used the AdaBoost algorithm to assemble the Softmax classifiers into recognizable images. This method resulted in a 3% increase of accuracy of the trained CNN models, and dramatically reduced the retraining time cost, and thus, it has good application prospects.

[1]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[2]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[3]  Thomas G. Dietterich.  Multiple Classifier Systems , 2000, Lecture Notes in Computer Science.

[4]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[5]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[6]  Xiaogang Wang,et al.  DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection , 2014, ArXiv.

[7]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

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

[9]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[10]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[11]  Ching Y. Suen,et al.  A trainable feature extractor for handwritten digit recognition , 2007, Pattern Recognit..

[12]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[13]  Kunihiko Fukushima,et al.  Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position , 1980, Biological Cybernetics.

[14]  Joshua B. Tenenbaum,et al.  The Large-Scale Structure of Semantic Networks: Statistical Analyses and a Model of Semantic Growth , 2001, Cogn. Sci..

[15]  Honglak Lee,et al.  Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations , 2009, ICML '09.

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

[17]  Syed Zubair,et al.  Dictionary learning based sparse coefficients for audio classification with max and average pooling , 2013, Digit. Signal Process..

[18]  Luca Maria Gambardella,et al.  Max-pooling convolutional neural networks for vision-based hand gesture recognition , 2011, 2011 IEEE International Conference on Signal and Image Processing Applications (ICSIPA).

[19]  Lars Kai Hansen,et al.  Neural Network Ensembles , 1990, IEEE Trans. Pattern Anal. Mach. Intell..