REGP: A NEW POOLING ALGORITHM FOR DEEP CONVOLUTIONAL NEURAL NETWORKS

In this paper, we propose a new pooling method for deep convolutional neural networks. Previously introduced pooling methods either have very simple assumptions or they depend on stochastic events. Different from those methods, RegP pooling intensely investigates the input data. The main idea of this approach is finding the most distinguishing parts in regions of the input by investigating neighborhood regions to construct the pooled representation. RegP pooling improves the efficiency of the learning process, which is clearly visible in the experimental results. Further, the proposed pooling method outperformed other widely used hand-crafted pooling methods on several benchmark datasets.

[1]  Yangdong Ye,et al.  Rank-based pooling for deep convolutional neural networks , 2016, Neural Networks.

[2]  Minho Lee,et al.  Deep learning with support vector data description , 2015, Neurocomputing.

[3]  Ling Shao,et al.  Generalized Pooling for Robust Object Tracking , 2016, IEEE Transactions on Image Processing.

[4]  Wen Gao,et al.  CSPS: An Adaptive Pooling Method for Image Classification , 2016, IEEE Transactions on Multimedia.

[5]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[6]  Jian Sun,et al.  Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Gustavo Carneiro,et al.  Combining deep learning and level set for the automated segmentation of the left ventricle of the heart from cardiac cine magnetic resonance , 2017, Medical Image Anal..

[8]  Yang Yang,et al.  Face image classification by pooling raw features , 2014, Pattern Recognit..

[9]  Luca Maria Gambardella,et al.  Convolutional Neural Network Committees for Handwritten Character Classification , 2011, 2011 International Conference on Document Analysis and Recognition.

[10]  N. Arunkumar,et al.  Convolutional neural network for bio-medical image segmentation with hardware acceleration , 2018, Cognitive Systems Research.

[11]  Andrea Vedaldi,et al.  MatConvNet: Convolutional Neural Networks for MATLAB , 2014, ACM Multimedia.

[12]  Svetlana Lazebnik,et al.  Multi-scale Orderless Pooling of Deep Convolutional Activation Features , 2014, ECCV.

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

[14]  Bingbing Ni,et al.  Robust geometric ℓp-norm feature pooling for image classification and action recognition , 2016, Image Vis. Comput..

[15]  Jing Pan,et al.  Learning Pooling for Convolutional Neural Network , 2017, Neurocomputing.

[16]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[17]  Cheng-Lin Liu,et al.  Adaptive spatial pooling for image classification , 2016, Pattern Recognit..

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

[19]  Sung Wook Baik,et al.  Efficient object-based surveillance image search using spatial pooling of convolutional features , 2017, J. Vis. Commun. Image Represent..

[20]  Yoshua Bengio,et al.  Editorial introduction to the Neural Networks special issue on Deep Learning of Representations , 2015, Neural Networks.

[21]  Fei-Fei Li,et al.  Large-Scale Video Classification with Convolutional Neural Networks , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[22]  Ko Nishino,et al.  The Scale of Geometric Texture , 2012, ECCV.

[23]  Nicolas Le Roux,et al.  Representational Power of Restricted Boltzmann Machines and Deep Belief Networks , 2008, Neural Computation.

[24]  Shifei Ding,et al.  A hybrid deep learning CNN-ELM model and its application in handwritten numeral recognition , 2015 .

[25]  Rob Fergus,et al.  Stochastic Pooling for Regularization of Deep Convolutional Neural Networks , 2013, ICLR.

[26]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[27]  Lei Wang,et al.  Encoding High Dimensional Local Features by Sparse Coding Based Fisher Vectors , 2014, NIPS.

[28]  Shuicheng Yan,et al.  Task-Driven Feature Pooling for Image Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[29]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[30]  Tinne Tuytelaars,et al.  Rank Pooling for Action Recognition , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.