Unsupervised Semantic-Based Aggregation of Deep Convolutional Features
Xu, Jian1,2; Wang, Chunheng2; Qi, Chengzuo1,2; Shi, Cunzhao2; Xiao, Baihua2
发表期刊IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN1057-7149
2019-02-01
卷号28期号:2页码:601-611
摘要

In this paper, we propose a simple but effective semantic-based aggregation (SBA) method. The proposed SBA utilizes the discriminative filters of deep convolutional layers as semantic detectors. Moreover, we propose the effective unsupervised strategy to select some semantic detectors to generate the "soft region proposals," which highlight certain discriminative pattern of objects and suppress the noise of background. The final global SBA representation could then be acquired by aggregating the regional representations weighted by the selected " soft region proposals" corresponding to various semantic content. Our unsupervised SBA is easy to generalize and achieves excellent performance on various tasks. We conduct comprehensive experiments and show that our unsupervised SBA outperforms the state-of-the-art unsupervised and supervised aggregation methods on image retrieval, place recognition, and cloud classification.

关键词Unsupervised semantic-based aggregation semantic detectors
DOI10.1109/TIP.2018.2867104
关键词[WOS]IMAGE RETRIEVAL ; SCALE ; CLASSIFICATION ; RECOGNITION
收录类别SCI
语种英语
资助项目National Natural Science Foundation of China[71621002] ; National Natural Science Foundation of China[61601462] ; National Natural Science Foundation of China[61531019] ; National Natural Science Foundation of China[61531019] ; National Natural Science Foundation of China[61601462] ; National Natural Science Foundation of China[71621002]
WOS研究方向Computer Science ; Engineering
WOS类目Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号WOS:000446255300006
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类图像视频处理与分析
引用统计
被引频次:22[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/25733
专题复杂系统管理与控制国家重点实验室_影像分析与机器视觉
通讯作者Wang, Chunheng
作者单位1.Univ Chinese Acad Sci, Beijing 100190, Peoples R China
2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
第一作者单位中国科学院自动化研究所
通讯作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Xu, Jian,Wang, Chunheng,Qi, Chengzuo,et al. Unsupervised Semantic-Based Aggregation of Deep Convolutional Features[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2019,28(2):601-611.
APA Xu, Jian,Wang, Chunheng,Qi, Chengzuo,Shi, Cunzhao,&Xiao, Baihua.(2019).Unsupervised Semantic-Based Aggregation of Deep Convolutional Features.IEEE TRANSACTIONS ON IMAGE PROCESSING,28(2),601-611.
MLA Xu, Jian,et al."Unsupervised Semantic-Based Aggregation of Deep Convolutional Features".IEEE TRANSACTIONS ON IMAGE PROCESSING 28.2(2019):601-611.
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
SBA.pdf(1963KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
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
[Xu, Jian]的文章
[Wang, Chunheng]的文章
[Qi, Chengzuo]的文章
百度学术
百度学术中相似的文章
[Xu, Jian]的文章
[Wang, Chunheng]的文章
[Qi, Chengzuo]的文章
必应学术
必应学术中相似的文章
[Xu, Jian]的文章
[Wang, Chunheng]的文章
[Qi, Chengzuo]的文章
相关权益政策
暂无数据
收藏/分享
文件名: SBA.pdf
格式: Adobe PDF
此文件暂不支持浏览
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。