Implicit Negative Sub-Categorization and Sink Diversion for Object Detection

doi:10.1109/TIP.2017.2779270

	Implicit Negative Sub-Categorization and Sink Diversion for Object Detection
	Li, Yu 1,2; Tang, Sheng 1,2; Lin, Min 3; Zhang, Yongdong 1,2; Li, Jintao 1,2; Yan, Shuicheng 3
	2018-04-01
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
卷号	27 期号:4 页码:1561-1574
摘要	In this paper, we focus on improving the proposal classification stage in the object detection task and present implicit negative sub-categorization and sink diversion to lift the performance by strengthening loss function in this stage. First, based on the observation that the "background" class is generally very diverse and thus challenging to be handled as a single indiscriminative class in existing state-of-the-art methods, we propose to divide the background category into multiple implicit sub-categories to explicitly differentiate diverse patterns within it. Second, since the ground truth class inevitably has low-value probability scores for certain images, we propose to add a "sink" class and divert the probabilities of wrong classes to this class when necessary, such that the ground truth label will still have a higher probability than other wrong classes even though it has low probability output. Additionally, we propose to use dilated convolution, which is widely used in the semantic segmentation task, for efficient and valuable context information extraction. Extensive experiments on PASCAL VOC 2007 and 2012 data sets show that our proposed methods based on faster R-CNN implementation can achieve state-of-the-art mAPs, i.e., 84.1%, 82.6%, respectively, and obtain 2.5% improvement on ILSVRC DET compared with that of ResNet.
关键词	Object detection convolutional neural network faster R-CNN classification loss context information
DOI	10.1109/TIP.2017.2779270
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61525206] ; National Natural Science Foundation of China[61572472] ; National Key Research and Development Program of China[2017YFB1002202] ; Beijing Natural Science Foundation[4152050] ; Key Research Program of CAS[KFZD-SW-407] ; STS Initiative of CAS[KFJ-STS-ZDTP-018]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000429463800001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：12[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/5936
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Tang, Sheng
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.AI Inst Qihoo 360, Beijing 100025, Peoples R China
推荐引用方式 GB/T 7714	Li, Yu,Tang, Sheng,Lin, Min,et al. Implicit Negative Sub-Categorization and Sink Diversion for Object Detection[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2018,27(4):1561-1574.
APA	Li, Yu,Tang, Sheng,Lin, Min,Zhang, Yongdong,Li, Jintao,&Yan, Shuicheng.(2018).Implicit Negative Sub-Categorization and Sink Diversion for Object Detection.IEEE TRANSACTIONS ON IMAGE PROCESSING,27(4),1561-1574.
MLA	Li, Yu,et al."Implicit Negative Sub-Categorization and Sink Diversion for Object Detection".IEEE TRANSACTIONS ON IMAGE PROCESSING 27.4(2018):1561-1574.