Efficient Parameter-Free Adaptive Multi-Modal Hashing

Efficient Parameter-Free Adaptive Multi-Modal Hashing
复制标题

高效无参数自适应多模态哈希

DOI:
10.1109/lsp.2020.3008335
复制
发表时间:
2020
影响因子:
3.9
通讯作者:
Huaxiang Zhang
Huaxiang Zhang
中科院分区:
工程技术2区
文献类型:
--
作者:
Chaoqun Zheng;Lei Zhu;Shusen Zhang;Huaxiang Zhang

文献摘要

参考文献

被引文献

相似文献

无监督多模式哈希算法以其存储成本低、检索速度快、不依赖于语义标签等优点,近年来在大规模多媒体检索研究领域受到广泛关注。然而,现有方法的模型学习过程仍然存在效率低下的问题:1)许多现有方法使用固定的通道权重来衡量不同通道的贡献。为了避免过度拟合,他们需要一个低效的超参数调整过程。2)现有的方法大多采用低效的优化策略来学习哈希码。在这封信中,我们提出了一种无监督的、高效的、无参数的自适应多模式散列(EPAMH)模型,以自适应地捕捉模式的变化,并将多模式特征的区分性语义保留到二进制哈希码中。此外,我们直接学习二进制码,操作简单有效,避免了量化误差的松弛,提高了模型学习效率。实验证明了EPAMH在三个公共多媒体检索数据集上的优越性能。我们的源代码和测试数据集可以在https://github.com/ChaoqunZheng/EPAMH.上获得
Unsupervised multi-modal hashing has recently attracted broad attention in research area of large-scale multimedia retrieval for its low storage cost, high retrieval speed, and independence on semantic labels. However, the model learning process of existing methods still suffer from the problem of low efficiency: 1) Many existing methods measure the contributions of different modalities using fixed modality weights. In order to avoid over-fitting, they need an inefficient hyper-parameter adjustment process. 2) Most existing methods adopt inefficient optimization strategies to learn hash codes. In this letter, we propose an unsupervised Efficient Parameter-free Adaptive Multi-modal Hashing (EPAMH) model to adaptively capture the modality variations and preserve the discriminative semantics of multi-modal features into the binary hash codes. Moreover, we directly learn the binary codes with simple and efficient operations, which prevents the relaxing quantization errors and improves the model learning efficiency. Experiments prove the superior performance of EPAMH on three public multimedia retrieval datasets. Our source codes and testing datasets can be obtained at https://github.com/ChaoqunZheng/EPAMH.
DOI: 10.1201/b10345-5
发表时间: 2010-11
期刊: Encyclopedia of Autism Spectrum Disorders
影响因子: --
作者:
Kim-Anh Lê Cao;Z. Welham
通讯作者: Kim-Anh Lê Cao;Z. Welham
用于可扩展多媒体检索的灵活多模式散列
DOI: 10.1145/3365841
发表时间: 2020-01
影响因子: 5
作者:
Lei Zhu;Xu Lu;Zhiyong Cheng;Jingjing Li;Huaxiang Zhang
通讯作者: Huaxiang Zhang
DOI: 10.1109/tip.2018.2863040
发表时间: 2019-01
影响因子: 10.6
作者:
Devraj Mandal;K. Chaudhury;S. Biswas
通讯作者: Devraj Mandal;K. Chaudhury;S. Biswas
DOI: 10.1145/3078971.3078981
发表时间: 2017-06
期刊: Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval
影响因子: --
作者:
Rui Yang;Yuliang Shi;Xin-Shun Xu
通讯作者: Rui Yang;Yuliang Shi;Xin-Shun Xu
DOI: 10.1109/tpami.2011.103
发表时间: 2012-01-01
影响因子: 23.6
作者:
Strecha, Christoph;Bronstein, Alexander M.;Fua, Pascal
通讯作者: Fua, Pascal