English 
谭晓阳

教授

招生学科专业:
计算机科学与技术 -- 【招收博士、硕士研究生】 -- 计算机科学与技术学院
软件工程 -- 【招收硕士研究生】 -- 计算机科学与技术学院
网络空间安全 -- 【招收博士、硕士研究生】 -- 计算机科学与技术学院
电子信息 -- 【招收博士、硕士研究生】 -- 计算机科学与技术学院

毕业院校:南京大学

学历:南京大学

学位:工学博士学位

所在单位:计算机科学与技术学院/人工智能学院/软件学院

办公地点:江宁校区 东区 计算机楼 218 办公室
http://parnec.nuaa.edu.cn/xtan

电子邮箱:

手机版

访问量:

最后更新时间:..

当前位置: 中文主页 >> 科学研究 >> 论文成果
Hierarchical deep hashing for image retrieval

点击次数:

所属单位:计算机科学与技术学院/人工智能学院/软件学院

发表刊物:FRONTIERS OF COMPUTER SCIENCE

关键字:image retrieval deep hashing hierarchical deep hashing

摘要:We present a new method to generate efficient multi-level hashing codes for image retrieval based on the deep siamese convolutional neural network (DSCNN). Conventional deep hashing methods trade off the capability of capturing highly complex and nonlinear semantic information of images against very compact hash codes, usually leading to high retrieval efficiency but with deteriorated accuracy. We alleviate the restrictive compactness requirement of hash codes by extending them to a two-level hierarchical coding scheme, in which the first level aims to capture the high-level semantic information extracted by the deep network using a rich encoding strategy, while the subsequent level squeezes them to more global and compact codes. At running time, we adopt an attention-based mechanism to select some of its most essential bits specific to each query image for retrieval instead of using the full hash codes of the first level. The attention-based mechanism is based on the guides of hash codes generated by the second level, taking advantage of both local and global properties of deep features. Experimental results on various popular datasets demonstrate the advantages of the proposed method compared to several state-of-the-art methods.

ISSN号:2095-2228

是否译文:

发表时间:2017-04-01

合写作者:Song, Ge

通讯作者:谭晓阳

版权所有©2018- 南京航空航天大学·信息化处(信息化技术中心)