Image Classification Using Convolutional Neural Networks and Kernel Extreme Learning Machines

We know that convolutional neural networks are good at learning invariant features, but not always optimal for classification. Contrarily, Kernel Extreme Learning Machines (KELMs) are good at approximating any target continuous function with extremely fast speed, but cannot learn complicated invariances. In this paper, we propose a novel image classification framework, in which KELM instead of Softmax function is adopted as a classifier in the convolutional neural network (CNN) architecture for promoting the performance of image classification. Experiments conducted on the publicly available datasets demonstrate the superior performance of the proposed method.

[1]  Ivor W. Tsang,et al.  DEFEATnet—A Deep Conventional Image Representation for Image Classification , 2016, IEEE Transactions on Circuits and Systems for Video Technology.

[2]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[3]  Jason Jianjun Gu,et al.  An Efficient Method for Traffic Sign Recognition Based on Extreme Learning Machine , 2017, IEEE Transactions on Cybernetics.

[4]  Jian Zhang,et al.  Convolutional Sparse Autoencoders for Image Classification , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[5]  Ching Y. Suen,et al.  A novel hybrid CNN-SVM classifier for recognizing handwritten digits , 2012, Pattern Recognit..

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

[7]  Qi Tian,et al.  Image-Specific Classification With Local and Global Discriminations , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[8]  Sergio Guadarrama,et al.  Im2Calories: Towards an Automated Mobile Vision Food Diary , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[9]  Abhinav Gupta,et al.  The Curious Robot: Learning Visual Representations via Physical Interactions , 2016, ECCV.

[10]  Vinod Vokkarane,et al.  DeepFood: Deep Learning-Based Food Image Recognition for Computer-Aided Dietary Assessment , 2016, ICOST.

[11]  Wei Liu,et al.  Classification by Retrieval: Binarizing Data and Classifiers , 2017, SIGIR.

[12]  Guang-Bin Huang,et al.  What are Extreme Learning Machines? Filling the Gap Between Frank Rosenblatt’s Dream and John von Neumann’s Puzzle , 2015, Cognitive Computation.

[13]  Femida Gwadry-Sridhar,et al.  Healthy Cognitive Aging: A Hybrid Random Vector Functional-Link Model for the Analysis of Alzheimer's Disease , 2017, AAAI.

[14]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Changsheng Li,et al.  Sparse representation for robust abnormality detection in crowded scenes , 2014, Pattern Recognit..

[16]  Chee Kheong Siew,et al.  Universal Approximation using Incremental Constructive Feedforward Networks with Random Hidden Nodes , 2006, IEEE Transactions on Neural Networks.

[17]  Niki Martinel,et al.  A supervised extreme learning committee for food recognition , 2016, Comput. Vis. Image Underst..

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

[19]  Antonio Torralba,et al.  Is Saki #delicious?: The Food Perception Gap on Instagram and Its Relation to Health , 2017, WWW.

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

[21]  Matthieu Guillaumin,et al.  Food-101 - Mining Discriminative Components with Random Forests , 2014, ECCV.

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

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

[24]  G. Griffin,et al.  Caltech-256 Object Category Dataset , 2007 .