Junhua Zou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Junhua Zou has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
Ting Rui
4 shared publications- Ting Rui
Unmanned Equipment Engineering Teaching and Research Office, Institute of Field Engineering, Army Engineering University of PLA, Nanjing, China
4 shared publications You Zhou
4 shared publicationsChengsong Yang
3 shared publicationsJian Tang
PLA University of Science and Technology
2 shared publicationsSai Zhang
2 shared publications
Latest Publications
- 17 November 2020
- Published by Springer Nature
- p. 563-579
Improving the Transferability of Adversarial Examples with Resized-Diverse-Inputs, Diversity-Ensemble and Region Fitting
- 17 November 2020
- Published by Springer Nature
- p. 563-579
Improving the Transferability of Adversarial Examples with Resized-Diverse-Inputs, Diversity-Ensemble and Region Fitting
- 1 August 2018
- Published by Elsevier in Computers and Electrical Engineering
- Vol. 70, 950-958
Convolutional neural network simplification via feature map pruning
- 1 August 2018
- Published by Elsevier in Computers and Electrical Engineering
- Vol. 70, 950-958
Convolutional neural network simplification via feature map pruning
- 10 May 2018
- Published by Springer Nature
- p. 869-879
Data Reconstruction Based on Supervised Deep Auto-Encoder
- 10 May 2018
- Published by Springer Nature
- p. 869-879
Data Reconstruction Based on Supervised Deep Auto-Encoder
- 1 March 2018
- Published by Springer Nature
- p. 290-299
Deep Auto-Encoder Based on Supervised Learning for Damaged Face Reconstruction
- 1 March 2018
- Published by Springer Nature
- p. 290-299
Deep Auto-Encoder Based on Supervised Learning for Damaged Face Reconstruction
- 1 November 2017
- Published by Springer Nature
- p. 249-256
ConvNets Pruning by Feature Maps Selection
- 26 May 2017
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 76 (23) , 25079-25089
Pedestrian detection based on multi-convolutional features by feature maps pruning
- 26 May 2017
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 76 (23) , 25079-25089
Pedestrian detection based on multi-convolutional features by feature maps pruning
- 18 April 2017
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 77 (9) , 10635-10649
Convolutional neural network feature maps selection based on LDA
- 18 April 2017
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 77 (9) , 10635-10649
Convolutional neural network feature maps selection based on LDA
- 1 December 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1207-1210
Convolutional Neural Network Simplification Based on Feature Maps Selection
We present a feature maps selection method for convolutional neural network (CNN) which can keep the classifier performance when CNN is used as a feature extractor. This method aims to simplify the last subsampling layer of CNN by cutting the number of feature maps with Linear Discriminant Analysis (LDA). It is shown that our method can stabilize the classification accuracy and achieve runtime reduction by removing some feature maps of the last subsampling layer which have worst separability. And the result also lay the foundation for further simplification of CNN.
- 1 December 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1207-1210
Convolutional Neural Network Simplification Based on Feature Maps Selection
We present a feature maps selection method for convolutional neural network (CNN) which can keep the classifier performance when CNN is used as a feature extractor. This method aims to simplify the last subsampling layer of CNN by cutting the number of feature maps with Linear Discriminant Analysis (LDA). It is shown that our method can stabilize the classification accuracy and achieve runtime reduction by removing some feature maps of the last subsampling layer which have worst separability. And the result also lay the foundation for further simplification of CNN.