Multi-View Linear Discriminant Analysis Network

Multi-View Linear Discriminant Analysis Network
复制标题

多视图线性判别分析网络

DOI:
10.1109/tip.2019.2913511
复制
发表时间:
2019-05
影响因子:
10.6
通讯作者:
Xiang Yong
Xiang Yong
中科院分区:
计算机科学1区
文献类型:
--
作者:
Hu Peng;Peng Dezhong;Sang Yongsheng;Xiang Yong

文献摘要

参考文献

被引文献

相似文献

在许多实际应用中,一个对象可以从多个视图或样式中描述,导致了新兴的多视图分析。为了消除复杂的(通常是高度非线性的)视图差异,有利的跨视图识别和检索,我们提出了一个多视图线性判别分析网络(MvLDAN),通过寻求一个非线性判别和视图不变的表示之间共享的多个视图。与现有的直接学习公共空间以减少视图间隙的多视图方法不同,我们的MvLDAN采用多个前馈神经网络(每个视图一个)和一种新的基于特征值的多视图目标函数,以将尽可能多的判别方差封装到所有可用的公共特征维度中。利用所提出的目标函数,MvLDAN可以产生具有以下特征的表示:1)同一类内的低方差,而不管视图差异,2)不同类之间的高方差,而不管视图差异,以及3)任何两个视图之间的高协方差。简而言之,在学习的多视图空间中,可以将所获得的深度特征投影到潜在公共空间中,在该潜在公共空间中,来自同一类的样本尽可能地彼此靠近(即使它们来自不同视图),并且来自不同类的样本尽可能地彼此远离(即使它们来自相同视图)。通过在5个数据库上进行的大量实验,与19种最先进的方法进行了比较,验证了该方法的有效性。
In many real-world applications, an object can be described from multiple views or styles, leading to the emerging multi-view analysis. To eliminate the complicated (usually highly nonlinear) view discrepancy for favorable cross-view recognition and retrieval, we propose a Multi-view Linear Discriminant Analysis Network (MvLDAN) by seeking a nonlinear discriminant and view-invariant representation shared among multiple views. Unlike existing multi-view methods which directly learn a common space to reduce the view gap, our MvLDAN employs multiple feedforward neural networks (one for each view) and a novel eigenvalue-based multi-view objective function to encapsulate as much discriminative variance as possible into all the available common feature dimensions. With the proposed objective function, the MvLDAN could produce representations possessing: 1) low variance within the same class regardless of view discrepancy, 2) high variance between different classes regardless of view discrepancy, and 3) high covariance between any two views. In brief, in the learned multi-view space, the obtained deep features can be projected into a latent common space in which the samples from the same class are as close to each other as possible (even though they are from different views), and the samples from different classes are as far from each other as possible (even though they are from the same view). The effectiveness of the proposed method is verified by extensive experiments carried out on five databases, in comparison with the 19 state-of-the-art approaches.
通过基于概率的语义保留散列进行跨视图检索
DOI: 10.1109/tcyb.2016.2608906
发表时间: 2017-12-01
影响因子: 11.8
作者:
Lin, Zijia;Ding, Guiguang;Wang, Jianmin
通讯作者: Wang, Jianmin
DOI: 10.1016/c2009-0-27872-x
发表时间: 1972
期刊:
影响因子: --
作者:
H. Shimodaira;Iain Murray
通讯作者: Iain Murray
DOI: 10.1109/cvpr.2007.382983
发表时间: 2007-06
期刊: 2007 IEEE Conference on Computer Vision and Pattern Recognition
影响因子: --
作者:
Huan Wang;Shuicheng Yan;Dong Xu;Xiaoou Tang;Thomas S. Huang
通讯作者: Huan Wang;Shuicheng Yan;Dong Xu;Xiaoou Tang;Thomas S. Huang
DOI: 10.1002/0470854774.ch1
发表时间: 2006
期刊: --
影响因子: --
作者:
P. Pudil;P. Somol;M. Haindl
通讯作者: P. Pudil;P. Somol;M. Haindl
DOI: 10.1007/bfb0015522
发表时间: 1996-04
期刊: --
影响因子: --
作者:
P. Belhumeur;J. Hespanha;D. Kriegman
通讯作者: P. Belhumeur;J. Hespanha;D. Kriegman