Semantic deep cross-modal hashing

Semantic deep cross-modal hashing
复制标题

语义深度跨模态哈希

DOI:
10.1016/j.neucom.2020.02.043
复制
发表时间:
2020-07
期刊:
影响因子:
6
通讯作者:
He Zhiquan
He Zhiquan
中科院分区:
计算机科学2区
文献类型:
--
作者:
Lin Qiubin;Cao Wenming;He Zhihai;He Zhiquan

文献摘要

参考文献

被引文献

相似文献

由于互联网上出现了越来越多的通道数据,跨通道检索已经成为一个不平凡的研究课题。此外,针对海量的跨通道数据及其高维的特征,哈希法可以降低存储成本,加快检索速度,因此人们对哈希法进行了探索。本文提出了一种深度跨模式散列方法,称为语义深度跨模式散列(SDCH)。它可以有效地利用语义标签信息,生成更具区别性的哈希码。具体地说,它利用语义标签分支对特征学习部分进行改进,既保留了已学习特征的语义信息,又保持了跨模式数据的不变性。此外,它还利用哈希码学习分支来维护汉明空间中不同模间的哈希码的一致性。此外,它还采用了模式间成对损失、交叉熵损失和量化损失,以确保所有相似实例对的排序相关性高于不同实例对的排序相关性。与最先进的注意力感知深度对抗散列(AADAH)方法相比,SDCH在IAPR TC-12、Mir-Flickr 25k和NUS-Wide三个广泛使用的数据集上的平均性能分别提高了6.14%、4.84%和3.75%。
Because an increasing number of modality data emerge on the Internet, cross-modal retrieval has become a nontrivial research topic. Furthermore, given the massive amount of cross-modal data and the high dimension of their features, hashing has been explored because it can reduce storage cost and accelerate retrieval speed. In this paper, we put forward a deep cross-modal hashing approach, dubbed semantic deep cross-modal hashing (SDCH). It can make effective use of semantic label information and generate more discriminative hash codes. Specifically, it utilizes the semantic label branches to improve the feature learning part, which can preserve semantic information of the learned features and keep the invariability of cross-modal data. Furthermore, it employs the hash codes learning branches to maintain the consistency of hash codes between different modalities in the Hamming space. Besides, it adopts inter-modal pairwise loss, cross-entropy loss and quantization loss to ensure that the ranking relevance of all similar instance pairs is higher than that of dissimilar ones. Compared to the most advanced method, attention-aware deep adversarial hashing (AADAH), SDCH averagely improves 6.14%, 4.84%, and 3.75% on three widely used datasets, IAPR TC-12, MIR-Flickr 25k, and NUS-WIDE, respectively.
DOI: 10.1609/aaai.v31i1.10719
发表时间: 2017-02
影响因子: 6.5
作者:
Erkun Yang;Cheng Deng;W. Liu;Xianglong Liu;D. Tao;Xinbo Gao
通讯作者: Erkun Yang;Cheng Deng;W. Liu;Xianglong Liu;D. Tao;Xinbo Gao
DOI: 10.1007/978-1-4612-4380-9_14
发表时间: 1936-12
期刊: Biometrika
影响因子: 2.7
作者:
H. Hotelling
通讯作者: H. Hotelling
DOI: --
发表时间: 2015-07
期刊: --
影响因子: --
作者:
Di Wang;Xinbo Gao;Xiumei Wang;Lihuo He
通讯作者: Di Wang;Xinbo Gao;Xiumei Wang;Lihuo He
用于图像理解的跨模态桥接和知识传输
DOI: 10.1109/tmm.2019.2903448
发表时间: 2019
影响因子: 7.3
作者:
Chenggang Yan;Liang Li;Chunjie Zhang;Bingtao Liu;Yongdong Zhang;Qionghai Dai
通讯作者: Qionghai Dai
DOI: 10.1145/2600428.2609610
发表时间: 2014-07
期刊: Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval
影响因子: --
作者:
J. Zhou;Guiguang Ding;Yuchen Guo
通讯作者: J. Zhou;Guiguang Ding;Yuchen Guo