OPT OpenIR  > 光学影像学习与分析中心
Weakly Supervised Object Detection via Object-Specific Pixel Gradient
Shen, Yunhang1; Ji, Rongrong1; Wang, Changhu2; Li, Xi3; Li, Xuelong4,5
Department光学影像学习与分析中心
2018-12
Source PublicationIEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
ISSN2162-237X;2162-2388
Volume29Issue:12Pages:5960-5970
Contribution Rank4
Abstract

Most existing object detection algorithms are trained based upon a set of fully annotated object regions or bounding boxes, which are typically labor-intensive. On the contrary, nowadays there is a significant amount of imagelevel annotations cheaply available on the Internet. It is hence a natural thought to explore such "weak" supervision to benefit the training of object detectors. In this paper, we propose a novel scheme to perform weakly supervised object localization, termed object-specific pixel gradient (OPG). The OPG is trained by using image-level annotations alone, which performs in an iterative manner to localize potential objects in a given image robustly and efficiently. In particular, we first extract an OPG map to reveal the contributions of individual pixels to a given object category, upon which an iterative mining scheme is further introduced to extract instances or components of this object. Moreover, a novel average and max pooling layer is introduced to improve the localization accuracy. In the task of weakly supervised object localization, the OPG achieves a state-of-the-art 44.5% top-5 error on ILSVRC 2013, which outperforms competing methods, including Oquab et al. and region-based convolutional neural networks on the Pascal VOC 2012, with gains of 2.6% and 2.3%, respectively. In the task of object detection, OPG achieves a comparable performance of 27.0% mean average precision on Pascal VOC 2007. In all experiments, the OPG only adopts the off-the-shelf pretrained CNN model, without using any object proposals. Therefore, it also significantly improves the detection speed, i.e., achieving three times faster compared with the stateof-the-art method.

KeywordConvolutional Neural Network (Cnn) Object Detection Weakly Supervised
DOI10.1109/TNNLS.2018.2816021
Indexed BySCI ; EI
Language英语
WOS IDWOS:000451230100014
PublisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
EI Accession Number20181605010365
Citation statistics
Document Type期刊论文
Identifierhttp://ir.opt.ac.cn/handle/181661/30739
Collection光学影像学习与分析中心
Corresponding AuthorJi, Rongrong
Affiliation1.Xiamen Univ, Sch Informat Sci & Engn, Fujian Key Lab Sensing & Comp Smart City, Xiamen 361005, Peoples R China
2.Toutiao AI Lab, Beijing 100098, Peoples R China
3.Zhejiang Univ, Coll Comp Sci & Technol, Hangzhou 310027, Zhejiang, Peoples R China
4.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Xian 710119, Shaanxi, Peoples R China
5.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
Recommended Citation
GB/T 7714
Shen, Yunhang,Ji, Rongrong,Wang, Changhu,et al. Weakly Supervised Object Detection via Object-Specific Pixel Gradient[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2018,29(12):5960-5970.
APA Shen, Yunhang,Ji, Rongrong,Wang, Changhu,Li, Xi,&Li, Xuelong.(2018).Weakly Supervised Object Detection via Object-Specific Pixel Gradient.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,29(12),5960-5970.
MLA Shen, Yunhang,et al."Weakly Supervised Object Detection via Object-Specific Pixel Gradient".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 29.12(2018):5960-5970.
Files in This Item:
File Name/Size DocType Version Access License
Weakly Supervised Ob(4529KB)期刊论文出版稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Shen, Yunhang]'s Articles
[Ji, Rongrong]'s Articles
[Wang, Changhu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Shen, Yunhang]'s Articles
[Ji, Rongrong]'s Articles
[Wang, Changhu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Shen, Yunhang]'s Articles
[Ji, Rongrong]'s Articles
[Wang, Changhu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Weakly Supervised Object Detection via Object-Specific Pixel Gradient.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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