Version 1
: Received: 12 September 2019 / Approved: 14 September 2019 / Online: 14 September 2019 (12:40:26 CEST)
How to cite:
Luo, L.; Kuang, H.; Liu, X.; Ma, X. DSRNet: A Novel Feature Extraction Network Achieving Trade off between Accuracy and Speed. Preprints2019, 2019090138
Luo, L.; Kuang, H.; Liu, X.; Ma, X. DSRNet: A Novel Feature Extraction Network Achieving Trade off between Accuracy and Speed. Preprints 2019, 2019090138
Luo, L.; Kuang, H.; Liu, X.; Ma, X. DSRNet: A Novel Feature Extraction Network Achieving Trade off between Accuracy and Speed. Preprints2019, 2019090138
APA Style
Luo, L., Kuang, H., Liu, X., & Ma, X. (2019). DSRNet: A Novel Feature Extraction Network Achieving Trade off between Accuracy and Speed. Preprints. https://doi.org/
Chicago/Turabian Style
Luo, L., Xinhua Liu and Xiaolin Ma. 2019 "DSRNet: A Novel Feature Extraction Network Achieving Trade off between Accuracy and Speed" Preprints. https://doi.org/
Abstract
It is important to reduce the computation complexity while maintaining the accuracy of convolution neural networks. We deem it is possible to further reduce the network complexity while ensuring the accuracy. In this paper, we propose a novel feature extraction network called DSRNet which is lightweight but effective. DSRNet follows the basic ideas of stacking modules and short connection, introduces Depthwise Separable convolution and utilizes the Dilated convolution. The proposed network has fewer parameters and achieves outstanding speed. We conducted comprehensive experiments on CIFAR10, CIFAR100 and STL10 datasets, and the results showed the DSRNet has great performance improvement in terms of accuracy and speed.
Computer Science and Mathematics, Computer Science
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.