Multi-Scale Residual Network for Image Classification
Xian Zhong, Oubo Gong, Wenxin Huang, Jingling Yuan, Bo Ma, Ryan Wen Liu
Abstract
Multi-scale approach representing image objects at various levels-of-details has been applied to various computer vision tasks. Existing image classification approaches place more emphasis on multi-scale convolution kernels, and overlook multi-scale feature maps. As such, some shallower information of the network will not be fully utilized. In this paper, we propose the Multi-Scale Residual (MSR) module that integrates multi-scale feature maps of the underlying information to the last layer of Convolutional Neural Network. Our proposed method significantly enhances the characteristics of the information in the final classification. Extensive experiments conducted on CIFAR100, Tiny-ImageNet and large-scale CalTech-256 datasets demonstrate the effectiveness of our method compared with Res-Family.
BibTeX
@inproceedings{icassp2020_multiscaleresidu,
title = {Multi-Scale Residual Network for Image Classification},
author = {Xian Zhong and Oubo Gong and Wenxin Huang and Jingling Yuan and Bo Ma and Ryan Wen Liu},
booktitle = {ICASSP 2020},
year = {2020}
}