Class-Imbalance Aware CNN Extension for High Resolution Aerial Image based Vehicle Localization and Categorization

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
会议名称	2017 2nd International Conference on Image, Vision and Computing
会议日期	2017-6
会议地点	中国四川成都
摘要	High 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.
收录类别	EI
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/14582
专题	综合信息系统研究中心
作者单位	1.中国科学院自动化所 2.中国科学院大学
推荐引用方式 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.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
V086-3.26.pdf（292KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载