Parametric local multiview hamming distance metric learning

Parametric local multiview hamming distance metric learning
复制标题

参数化局部多视图汉明距离度量学习

DOI:
10.1016/j.patcog.2017.06.018
复制
发表时间:
2018-03
影响因子:
8
通讯作者:
Wen Gao
Wen Gao
中科院分区:
计算机科学1区
文献类型:
--
作者:
Deming Zhai;Xianming Liu;Hong Chang;Yi Zhen;Xilin Chen;Maozu Guo;Wen Gao

文献摘要

参考文献

被引文献

相似文献

学习合适的距离度量是模式识别中的一个关键问题。为了应对海量数据的可扩展性问题,二进制码上的汉明距离被提倡,因为它允许精确的亚线性KNN搜索,同时具有高效存储的优势。在本文中,我们研究了在多模式数据环境下用于跨视点相似性搜索的Hamming度量学习。我们提出了一种新的方法,称为参数局部多视点汉明度量(PLMH),该方法基于一组局部哈希函数来学习多视点度量,以局部地适应每个通道的数据结构。为了平衡局部性和计算效率,每个实例的散列投影矩阵被参数化,并且具有保证的逼近误差界,作为与一小部分锚点相关联的基本散列投影的线性组合。由成对约束和三元组约束提供的弱监督信息(边信息)被以一致的方式合并以获得语义上有效的哈希码。设计了一种具有正交旋转的局部最优共轭梯度算法来学习每个比特的哈希函数,并以顺序的方式学习整个哈希码以逐步最小化偏差。对跨媒体检索任务的实验评估表明,PLMH的性能与最先进的方法相比具有竞争力。
Learning an appropriate distance metric is a crucial problem in pattern recognition. To confront with the scalability issue of massive data, hamming distance on binary codes is advocated since it permits exact sub-linear kNN search and meanwhile shares the advantage of efficient storage. In this paper, we study hamming metric learning in the context of multimodal data for cross-view similarity search. We present a new method called Parametric Local Multiview Hamming metric (PLMH), which learns multiview metric based on a set of local hash functions to locally adapt to the data structure of each modality. To balance locality and computational efficiency, the hash projection matrix of each instance is parameterized, with guaranteed approximation error bound, as a linear combination of basis hash projections associated with a small set of anchor points. The weak-supervisory information (side information) provided by pairwise and triplet constraints are incorporated in a coherent way to achieve semantically effective hash codes. A local optimal conjugate gradient algorithm with orthogonal rotations is designed to learn the hash functions for each bit, and the overall hash codes are learned in a sequential manner to progressively minimize the bias. Experimental evaluations on cross-media retrieval tasks demonstrate that PLMH performs competitively against the state-of-the-art methods.
DOI: 10.1023/b:visi.0000029664.99615.94
发表时间: 2004-11-01
影响因子: 19.5
作者:
Lowe, DG
通讯作者: Lowe, DG
DOI: --
发表时间: 2012-12
期刊: --
影响因子: --
作者:
Yi Zhen;D. Yeung
通讯作者: Yi Zhen;D. Yeung
DOI: --
发表时间: 2003-08
期刊: --
影响因子: --
作者:
Aharon Bar-Hillel;T. Hertz;N. Shental;D. Weinshall
通讯作者: Aharon Bar-Hillel;T. Hertz;N. Shental;D. Weinshall
DOI: 10.1145/2487575.2487668
发表时间: 2013-08
期刊: Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining
影响因子: --
作者:
Mingdong Ou;Peng Cui;Fei Wang;Jun Wang;Wenwu Zhu;Shiqiang Yang
通讯作者: Mingdong Ou;Peng Cui;Fei Wang;Jun Wang;Wenwu Zhu;Shiqiang Yang
DOI: --
发表时间: 2011-06
期刊: --
影响因子: --
作者:
Mohammad Norouzi;David J. Fleet
通讯作者: Mohammad Norouzi;David J. Fleet