版权说明 操作指南
首页 > 成果 > 详情

Self-Supervised Locality-Sensitive Deep Hashing for the Robust Retrieval of Degraded Images

认领
导出
Link by DOI
反馈
分享
QQ微信 微博
成果类型:
期刊论文
作者:
Xiang, Lingyun;Hu, Hailang;Li, Qian;Yu, Hao;Shen, Xiaobo
通讯作者:
Shen, XB
作者机构:
[Hu, Hailang; Xiang, Lingyun] Changsha Univ Sci & Technol, Sch Comp & Commun Engn, Changsha 410114, Peoples R China.
[Xiang, Lingyun] Nanjing Univ Informat Sci & Technol, Engn Res Ctr Digital Forens, Minist Educ, Nanjing 210044, Peoples R China.
[Hu, Hailang] Changsha Res Inst Min & Met Co Ltd, Changsha 410012, Peoples R China.
[Li, Qian] North China Inst Comp Technol, Beijing 100083, Peoples R China.
[Yu, Hao] Tech Univ Munich, Fak Informat, D-85748 Munich, Germany.
通讯机构:
[Shen, XB ] N
Nanjing Univ Sci & Technol, Sch Comp Sci & Engn, Nanjing 210094, Peoples R China.
语种:
英文
关键词:
Image retrieval;Codes;Semantics;Training;Robustness;Approximation algorithms;Quantization (signal);Vectors;Hash functions;Hands;Degraded image;large-scale image retrieval;locality-sensitive;self-supervised deep hashing
期刊:
IEEE Transactions on Information Forensics and Security
ISSN:
1556-6013
年:
2025
卷:
20
页码:
1582-1596
基金类别:
10.13039/501100001809-National Natural Science Foundation of China (Grant Number: 61972057, 62472226, 62176126 and 62172059) 10.13039/501100004608-Natural Science Foundation of Jiangsu Province, China (Grant Number: BK20230095)
机构署名:
本校为第一机构
院系归属:
计算机与通信工程学院
摘要:
Recently, numerous degraded images have flooded search engines and social networks, finding extensive and practical applications in the real world. However, these images have also posed new challenges to conventional image retrieval tasks. To this end, we introduce a new task of retrieving degraded images through deep hashing from large-scale databases, and further present the Locality-Sensitive Hashing Network (LSHNet) to tackle it in a self-supervised manner. More specifically, we first propose a triplet strategy to enable the self-supervised training of LSHNet in an end-to-end fashion. Due ...

反馈

验证码:
看不清楚,换一个
确定
取消

成果认领

标题:
用户 作者 通讯作者
请选择
请选择
确定
取消

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com