CASIA OpenIR  > 复杂系统管理与控制国家重点实验室  > 深度强化学习
A Visual Attention based Convolutional Neural Network for Image Classification
Chen Yaran1; Zhao Dongbin1; Lv Le1; Li Chengdong2
2016-09
Conference NameThe 2016 World Congress on Intelligent Control and Automation
Conference Date12-15 June 2016
Conference PlaceGuilin, China
AbstractThis paper presents a visual attention based convolutional neural network (CNN) to solve the image classification problem in the real complex world scene. The presented method can simulate the process of recognizing objects and find the area of interest which is related with the task. Compared with the CNN method in image classification, the model is proficient in fine-grained classification problem and has a better robustness due to its mechanism of multi-glance and visual attention. We evaluate the model on vehicle dataset, where its performance exceeds CNN baseline on image classification.
DOI10.1109/WCICA.2016.7578651
Citation statistics
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/14478
Collection复杂系统管理与控制国家重点实验室_深度强化学习
Affiliation1.he State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
2.he School of Information and Electrical Engineer- ing, Shandong Jianzhu University, Jinan 250101, China (
Recommended Citation
GB/T 7714
Chen Yaran,Zhao Dongbin,Lv Le,et al. A Visual Attention based Convolutional Neural Network for Image Classification[C],2016.
Files in This Item: Download All
File Name/Size DocType Version Access License
07578651.pdf(540KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Chen Yaran]'s Articles
[Zhao Dongbin]'s Articles
[Lv Le]'s Articles
Baidu academic
Similar articles in Baidu academic
[Chen Yaran]'s Articles
[Zhao Dongbin]'s Articles
[Lv Le]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Chen Yaran]'s Articles
[Zhao Dongbin]'s Articles
[Lv Le]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 07578651.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.