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
作者部门光学影像学习与分析中心
2018-12
发表期刊IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
ISSN2162-237X;2162-2388
卷号29期号:12页码:5960-5970
产权排序4
摘要

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.

关键词Convolutional Neural Network (Cnn) Object Detection Weakly Supervised
DOI10.1109/TNNLS.2018.2816021
收录类别SCI
语种英语
WOS记录号WOS:000451230100014
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型期刊论文
条目标识符http://ir.opt.ac.cn/handle/181661/30739
专题光学影像学习与分析中心
通讯作者Ji, Rongrong
作者单位1.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
推荐引用方式
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.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Weakly Supervised Ob(4529KB)期刊论文出版稿开放获取CC BY-NC-SA浏览 请求全文
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Shen, Yunhang]的文章
[Ji, Rongrong]的文章
[Wang, Changhu]的文章
百度学术
百度学术中相似的文章
[Shen, Yunhang]的文章
[Ji, Rongrong]的文章
[Wang, Changhu]的文章
必应学术
必应学术中相似的文章
[Shen, Yunhang]的文章
[Ji, Rongrong]的文章
[Wang, Changhu]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Weakly Supervised Object Detection via Object-Specific Pixel Gradient.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。