Article
Version 1
This version is not peer-reviewed
DSRNet: A Novel Feature Extraction Network Achieving Trade off between Accuracy and Speed
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. Preprints 2019, 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
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.
Keywords
depthwise; dilated; neural network;network complexity
Subject
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.
Comments (0)
We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.
Leave a public commentSend a private comment to the author(s)
* All users must log in before leaving a comment