CASIA OpenIR  > 综合信息系统研究中心
Class-Imbalance Aware CNN Extension for High Resolution Aerial Image based Vehicle Localization and Categorization
Li FM(李非墨)1,2; Li SX(李书晓)1; Zhu CF(朱承飞)1; Lan XS(兰晓松)1,2; Chang HX(常红星)1
2017-12
Conference Name2017 2nd International Conference on Image, Vision and Computing
Conference Date2017-6
Conference Place中国四川成都
AbstractHigh resolution aerial image based vehicle localization and categorization methods are crucial for many real life applications. Convolutional neural network based classifiers have already achieved very high performances, but are still suffering from the problem of class imbalance. To address this issue, an efficient bi-parted style network extension scheme based on a class-imbalance aware loss function is proposed.  This novel loss function is devised by adding an extra class-imbalance aware regularization term to the normal softmax loss, and will force the feature maps in the extended network structure to be more sensitive to samples from the minority classes. This network extension is compared with its strong equivalent counter-parts in experiment, and comparably significant improvements on the minority classes can be observed.
Indexed ByEI
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/14582
Collection综合信息系统研究中心
Affiliation1.中国科学院自动化所
2.中国科学院大学
Recommended Citation
GB/T 7714
Li FM,Li SX,Zhu CF,et al. Class-Imbalance Aware CNN Extension for High Resolution Aerial Image based Vehicle Localization and Categorization[C],2017.
Files in This Item: Download All
File Name/Size DocType Version Access License
V086-3.26.pdf(292KB)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
[Li FM(李非墨)]'s Articles
[Li SX(李书晓)]'s Articles
[Zhu CF(朱承飞)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Li FM(李非墨)]'s Articles
[Li SX(李书晓)]'s Articles
[Zhu CF(朱承飞)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Li FM(李非墨)]'s Articles
[Li SX(李书晓)]'s Articles
[Zhu CF(朱承飞)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: V086-3.26.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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