Convolutional neural network feature maps selection based on LDA

Convolutional neural network (CNN), as widely applied to vision and speech, has developed lager and lager network size in last few years. In this paper, we propose a CNN feature maps selection method which can simplify CNN structure on the premise of stabilize the classifier performance. Our approach aims to cut the feature map number of the last subsampling layer and achieves shortest runtime on the basis of Linear Discriminant Analysis (LDA). We rebuild feature maps selection formula based on the between-class scatter matrix and within-class scatter matrix, because LDA can lead to information loss in the dimension-reduction process. Our experiments measure on two standard datasets and a dataset made by ourselves. According to the separability value of each feature map, we suggest the least number of feature maps which can keep the classifier performance. Furthermore, we prove that separability value is an effective indicator for reference to select feature maps.

[1]  Tongwei Ren,et al.  Salient object detection for RGB-D image via saliency evolution , 2016, 2016 IEEE International Conference on Multimedia and Expo (ICME).

[2]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[3]  Huimin Lu,et al.  Underwater image de-scattering and classification by deep neural network , 2016, Comput. Electr. Eng..

[4]  Chengjun Liu,et al.  Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition , 2002, IEEE Trans. Image Process..

[5]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[7]  Ran El-Yaniv,et al.  Binarized Neural Networks , 2016, NIPS.

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

[9]  Ming Yang,et al.  DeepFace: Closing the Gap to Human-Level Performance in Face Verification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Trevor Darrell,et al.  PANDA: Pose Aligned Networks for Deep Attribute Modeling , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Jing Liu,et al.  Elastic Edge Boxes for Object Proposal on RGB-D Images , 2016, MMM.

[12]  Huimin Lu,et al.  Single image dehazing through improved atmospheric light estimation , 2015, Multimedia Tools and Applications.

[13]  Yixin Chen,et al.  Compressing Neural Networks with the Hashing Trick , 2015, ICML.

[14]  Jing Liu,et al.  Object proposal on RGB-D images via elastic edge boxes , 2017, Neurocomputing.

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

[16]  Miao Sun,et al.  Generic Object Detection with Dense Neural Patterns and Regionlets , 2014, BMVC.

[17]  Yan Liu,et al.  Soft-assigned bag of features for object tracking , 2014, Multimedia Systems.

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

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

[20]  Bin Li,et al.  Wound intensity correction and segmentation with convolutional neural networks , 2017, Concurr. Comput. Pract. Exp..

[21]  Camille Couprie,et al.  Learning Hierarchical Features for Scene Labeling , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Song Han,et al.  Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding , 2015, ICLR.

[23]  Robert P. W. Duin,et al.  Linear dimensionality reduction via a heteroscedastic extension of LDA: the Chernoff criterion , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Hanan Samet,et al.  Pruning Filters for Efficient ConvNets , 2016, ICLR.

[25]  Qiang Chen,et al.  Network In Network , 2013, ICLR.

[26]  Stefan Carlsson,et al.  CNN Features Off-the-Shelf: An Astounding Baseline for Recognition , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[27]  Yoshua Bengio,et al.  BinaryNet: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1 , 2016, ArXiv.

[28]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  Ming Yang,et al.  3D Convolutional Neural Networks for Human Action Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Xiaogang Wang,et al.  Sparsifying Neural Network Connections for Face Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[31]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[32]  Xiang Zhang,et al.  OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks , 2013, ICLR.

[33]  Ming Yang,et al.  Compressing Deep Convolutional Networks using Vector Quantization , 2014, ArXiv.

[34]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[35]  B. Scholkopf,et al.  Fisher discriminant analysis with kernels , 1999, Neural Networks for Signal Processing IX: Proceedings of the 1999 IEEE Signal Processing Society Workshop (Cat. No.98TH8468).

[36]  Yan Liu,et al.  How important is location information in saliency detection of natural images , 2015, Multimedia Tools and Applications.