Deep Momentum Uncertainty Hashing | |
Fu, Chaoyou1,3,4; Wang, Guoli5; Wu, Xiang3; Zhang, Qian6; He, Ran1,2,3,4 | |
发表期刊 | Pattern Recognition |
2022 | |
卷号 | 122页码:108264 |
摘要 | Combinatorial optimization (CO) has been a hot research topic because of its theoretic and practical importance. As a classic CO problem, deep hashing aims to find an optimal code for each data from finite discrete possibilities, while the discrete nature brings a big challenge to the optimization process. Previous methods usually mitigate this challenge by binary approximation, substituting binary codes for real-values via activation functions or regularizations. However, such approximation leads to uncertainty between real-values and binary ones, degrading retrieval performance. In this paper, we propose a novel Deep Momentum Uncertainty Hashing (DMUH). It explicitly estimates the uncertainty during training and leverages the uncertainty information to guide the approximation process. Specifically, we model bit- level uncertainty via measuring the discrepancy between the output of a hashing network and that of a momentum-updated network. The discrepancy of each bit indicates the uncertainty of the hashing network to the approximate output of that bit. Meanwhile, the mean discrepancy of all bits in a hashing code can be regarded as image-level uncertainty. It embodies the uncertainty of the hashing network to the corresponding input image. The hashing bit and image with higher uncertainty are paid more attention during optimization. To the best of our knowledge, this is the first work to study the uncertainty in hashing bits. Extensive experiments are conducted on four datasets to verify the superiority of our method, including CIFAR-10, NUS-WIDE, MS-COCO, and a million-scale dataset Clothing1M. Our method achieves the best performance on all of the datasets and surpasses existing state-of-the-art methods by a large margin. |
关键词 | Combinatorial optimization Deep hashing Uncertainty |
语种 | 英语 |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48690 |
专题 | 模式识别实验室 |
通讯作者 | Fu, Chaoyou; He, Ran |
作者单位 | 1.National Laboratory of Pattern Recognition, CASIA 2.Center for Excellence in Brain Science and Intelligence Technology, CAS 3.Center for Research on Intelligent Perception and Computing, CASIA 4.School of Artificial Intelligence, University of Chinese Academy of Sciences 5.Department of Automation, Tsinghua University 6.Horizon Robotics |
第一作者单位 | 中国科学院自动化研究所; 模式识别国家重点实验室 |
通讯作者单位 | 中国科学院自动化研究所; 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Fu, Chaoyou,Wang, Guoli,Wu, Xiang,et al. Deep Momentum Uncertainty Hashing[J]. Pattern Recognition,2022,122:108264. |
APA | Fu, Chaoyou,Wang, Guoli,Wu, Xiang,Zhang, Qian,&He, Ran.(2022).Deep Momentum Uncertainty Hashing.Pattern Recognition,122,108264. |
MLA | Fu, Chaoyou,et al."Deep Momentum Uncertainty Hashing".Pattern Recognition 122(2022):108264. |
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 | ||
PR.pdf(1803KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论