PLANET: Improved Convolutional Neural Networks with Image Enhancement for Image Classification

In the past few years, deep learning has become a research hotspot and has had a profound impact on computer vision. Deep CNN has been proven to be the most important and effective model for image processing, but due to the lack of training samples and huge number of learning parameters, it is easy to tend to overfit. In this work, we propose a new two-stage CNN image classification network, named “Improved Convolutional Neural Networks with Image Enhancement for Image Classification” and PLANET in abbreviation, which uses a new image data enhancement method called InnerMove to enhance images and augment the number of training samples. InnerMove is inspired by the “object movement” scene in computer vision and can improve the generalization ability of deep CNN models for image classification tasks. Sufficient experiment results show that PLANET utilizing InnerMove for image enhancement outperforms the comparative algorithms, and InnerMove has a more significant effect than the comparative data enhancement methods for image classification tasks.

[1]  Catarina Eloy,et al.  Classification of breast cancer histology images using Convolutional Neural Networks , 2017, PloS one.

[2]  Catarina Eloy,et al.  BACH: Grand Challenge on Breast Cancer Histology Images , 2018, Medical Image Anal..

[3]  Seong Joon Oh,et al.  CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

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

[5]  Mehran Ebrahimi,et al.  Two-Stage Convolutional Neural Network for Breast Cancer Histology Image Classification , 2018, ICIAR.

[6]  Jason Weston,et al.  Natural Language Processing (Almost) from Scratch , 2011, J. Mach. Learn. Res..

[7]  Hongyi Zhang,et al.  mixup: Beyond Empirical Risk Minimization , 2017, ICLR.

[8]  Yi Yang,et al.  Random Erasing Data Augmentation , 2017, AAAI.

[9]  Yi Yang,et al.  PatchShuffle Regularization , 2017, ArXiv.

[10]  Graham W. Taylor,et al.  Improved Regularization of Convolutional Neural Networks with Cutout , 2017, ArXiv.

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

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

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

[14]  William Zhu,et al.  Relationship among basic concepts in covering-based rough sets , 2009, Inf. Sci..

[15]  Brendan J. Frey,et al.  Adaptive dropout for training deep neural networks , 2013, NIPS.

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

[17]  Takashi Matsubara,et al.  Data Augmentation Using Random Image Cropping and Patching for Deep CNNs , 2018, IEEE Transactions on Circuits and Systems for Video Technology.

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

[19]  William Zhu,et al.  Relationship between generalized rough sets based on binary relation and covering , 2009, Inf. Sci..

[20]  Thomas B. Moeslund,et al.  A Survey of Computer Vision-Based Human Motion Capture , 2001, Comput. Vis. Image Underst..

[21]  Chaoqun Hong,et al.  Exploiting geometrical structures using Autoencoders and click data for image re-ranking , 2017, Neurocomputing.

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

[23]  Yann LeCun,et al.  Regularization of Neural Networks using DropConnect , 2013, ICML.

[24]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.