.png){kind=icon}
返回
Deep Supervised Hashing Based on Stable Distribution
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2019.2900489.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Recently, the convolutional neural network (CNN)-based hashing method has achieved its promising performance for image retrieval. However, tackling the discrepancy between quantization error minimization and discriminability maximization of the network outputs simultaneously still remains unsolved. Distinguished from the previous works, which only can search an equilibrium point within the discrepancy, we propose a novel deep supervised hashing based on stable distribution (DSHSD) to eliminate the discrepancy with distribution consistency guarantee. First, we utilize a smooth projection function, in which the amount of smoothing is adaptable, to relax the discrete constraint instead of any quantization regularizer. Second, a mathematical connection between the smooth projection and the feature distribution is made to maintain distribution consistency. A relaxed multi-semantic information fusion method is implemented to make hash codes learned to preserve more semantic information and accelerate the training convergence. According to stable distribution, we propose a novel hashing framework to eliminate the discrepancy and support fast image retrieval. The extensive experiments on the CIFAR-10, NUS-WIDE, and ImageNet datasets show that our method can outperform the state-of-the-art methods from various perspectives.
Keyword:
Supervised hashing
stable distribution
distribution consistency
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
暂无机构信息
引用论文
Learning unified binary codes for cross-modal retrieval via latent semantic hashing.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏Rottlerin exhibits antitumor activity via down-regulation of TAZ in non-small cell lung cancerOncotarget
OAAI
OncotargetIF0
OAAI分享收藏
查看更多内容