中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Implicit Negative Sub-Categorization and Sink Diversion for Object Detection

文献类型：期刊论文

作者Li, Yu1,3; Tang, Sheng1,3; Lin, Min2; Zhang, Yongdong1,3; Li, Jintao1,3; Yan, Shuicheng2
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2018-04-01
卷号27期号:4页码:1561-1574
关键词Object detection convolutional neural network faster R-CNN classification loss context information
ISSN号1057-7149
DOI10.1109/TIP.2017.2779270
英文摘要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.
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
语种英语
WOS记录号WOS:000429463800001
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://119.78.100.204/handle/2XEOYT63/5935]  
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.AI Inst Qihoo 360, Beijing 100025, Peoples R China
3.Univ Chinese Acad Sci, Beijing 100049, 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.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。