A General Framework for Deep Supervised Discrete Hashing

A General Framework for Deep Supervised Discrete Hashing
复制标题

深度监督离散散列的通用框架

DOI:
10.1007/s11263-020-01327-w
复制
发表时间:
2020-04
影响因子:
19.5
通讯作者:
Tieniu Tan
Tieniu Tan
中科院分区:
计算机科学2区
文献类型:
--
作者:
Qi Li;Zhenan Sun;Ran He;Tieniu Tan

文献摘要

参考文献

被引文献

相似文献

随着网络上图像和视频数据的快速增长,散列算法近年来被广泛研究用于图像或视频搜索。受益于深度学习的最新进展,深度哈希方法已经显示出优于传统哈希方法的上级性能。然而,先前的深度散列方法存在一些限制(例如,语义信息未被充分利用)。在本文中,我们开发了一个通用的深度监督离散散列框架,该框架基于学习的二进制代码应该是理想的分类的假设。相似性信息和分类信息都用于在一个流框架内学习散列码。我们直接将最后一层的输出限制为二进制代码,这在深度哈希算法中很少研究。此外,本文还利用了两两相似度信息和三元组排序信息。此外,两个不同的损失函数:损失和铰链损失,这是精心设计的分类项下的一个流框架。由于散列码的离散性,交替最小化方法被用来优化目标函数。实验结果表明,我们的方法优于目前最先进的方法在基准数据集。
With the rapid growth of image and video data on the web, hashing has been extensively studied for image or video search in recent years. Benefiting from recent advances in deep learning, deep hashing methods have shown superior performance over the traditional hashing methods. However, there are some limitations of previous deep hashing methods (e.g., the semantic information is not fully exploited). In this paper, we develop a general deep supervised discrete hashing framework based on the assumption that the learned binary codes should be ideal for classification. Both the similarity information and the classification information are used to learn the hash codes within one stream framework. We constrain the outputs of the last layer to be binary codes directly, which is rarely investigated in deep hashing algorithms. Besides, both the pairwise similarity information and the triplet ranking information are exploited in this paper. In addition, two different loss functions are presented:loss and hinge loss, which are carefully designed for the classification term under the one stream framework. Because of the discrete nature of hash codes, an alternating minimization method is used to optimize the objective function. Experimental results have shown that our approach outperforms current state-of-the-art methods on benchmark datasets.
DOI: --
发表时间: 2018
期刊: --
影响因子: --
作者:
Shupeng Su;Chao Zhang-;Kai Han;Yonghong Tian
通讯作者: Shupeng Su;Chao Zhang-;Kai Han;Yonghong Tian
DOI: --
发表时间: 2016-11
期刊: ArXiv
影响因子: --
作者:
G. Koutaki;K. Shirai;Mitsuru Ambai
通讯作者: G. Koutaki;K. Shirai;Mitsuru Ambai
DOI: 10.1145/2502081.2502100
发表时间: 2013-10
期刊: Proceedings of the 21st ACM international conference on Multimedia
影响因子: --
作者:
Jianfeng Wang;Jingdong Wang;Nenghai Yu;Shipeng Li
通讯作者: Jianfeng Wang;Jingdong Wang;Nenghai Yu;Shipeng Li
DOI: 10.1609/aaai.v30i1.10176
发表时间: 2016-02
期刊: --
影响因子: --
作者:
Wang-Cheng Kang;Wu-Jun Li;Zhi-Hua Zhou
通讯作者: Wang-Cheng Kang;Wu-Jun Li;Zhi-Hua Zhou
DOI: --
发表时间: 2009-12
期刊: --
影响因子: --
作者:
M. Raginsky;Svetlana Lazebnik
通讯作者: M. Raginsky;Svetlana Lazebnik