DSRNet: A Novel Feature Extraction Network Achieving Trade off between Accuracy and Speed
Laigan Luo, Hailan Kuang, Xinhua Liu, Xiaolin Ma · 2019
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. 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.