Trace Quotient with Sparsity Priors for Learning Low Dimensional Image Representations

Trace Quotient with Sparsity Priors for Learning Low Dimensional Image Representations
复制标题

具有稀疏先验的迹商用于学习低维图像表示

DOI:
10.1109/tpami.2019.2921031
复制
发表时间:
2018-10
期刊:
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
影响因子:
--
通讯作者:
Martin Kleinsteuber
Martin Kleinsteuber
中科院分区:
其他
文献类型:
--
作者:
Xian Wei;Hao Shen;Martin Kleinsteuber

文献摘要

参考文献

被引文献

相似文献

这项工作研究了学习适当的低维图像表示的问题。我们提出了一个通用的算法框架,它利用了两个经典的表示学习范式,即,稀疏表示和迹商准则,以解开高维图像中变化的潜在因素。具体来说,我们的目标是通过将迹商标准应用于精心设计的稀疏表示来学习低维判别因子的简单表示。我们构建了一个统一的成本函数,被称为SPARse低维表示(SparLow)函数,用于联合学习稀疏化字典和降维变换。SparLow函数广泛适用于在三种经典机器学习场景中开发各种算法,即无监督,监督和半监督学习。为了开发有效的联合学习算法,最大限度地提高SparLow函数,我们部署了一个框架的稀疏编码与适当的凸先验,以确保稀疏表示是局部可微的。此外,我们开发了一个有效的几何共轭梯度算法,以最大化其基础黎曼流形上的SparLow函数。SparLow算法框架的性能进行了研究的几个图像处理任务,如三维数据可视化,人脸/数字识别,对象/场景分类。
This work studies the problem of learning appropriate low dimensional image representations. We propose a generic algorithmic framework, which leverages two classic representation learning paradigms, i.e., sparse representation and the trace quotient criterion, to disentangle underlying factors of variation in high dimensional images. Specifically, we aim to learn simple representations of low dimensional, discriminant factors by applying the trace quotient criterion to well-engineered sparse representations. We construct a unified cost function, coined as the SPARse LOW dimensional representation (SparLow) function, for jointly learning both a sparsifying dictionary and a dimensionality reduction transformation. The SparLow function is widely applicable for developing various algorithms in three classic machine learning scenarios, namely, unsupervised, supervised, and semi-supervised learning. In order to develop efficient joint learning algorithms for maximizing the SparLow function, we deploy a framework of sparse coding with appropriate convex priors to ensure the sparse representations to be locally differentiable. Moreover, we develop an efficient geometric conjugate gradient algorithm to maximize the SparLow function on its underlying Riemannian manifold. Performance of the proposed SparLow algorithmic framework is investigated on several image processing tasks, such as 3D data visualization, face/digit recognition, and object/scene categorization.
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: 2001
期刊: --
影响因子: --
作者:
P. Belhumeur;D. Kriegman
通讯作者: P. Belhumeur;D. Kriegman
DOI: 10.1109/tpami.2005.55
发表时间: 2005-03-01
影响因子: 23.6
作者:
He, XF;Yan, SC;Zhang, HJ
通讯作者: Zhang, HJ
DOI: --
发表时间: 2008
期刊: --
影响因子: --
作者:
Geoffrey E. Hinton
通讯作者: Geoffrey E. Hinton
DOI: 10.2307/3616746
发表时间: 1980-05
期刊: --
影响因子: --
作者:
Patrick Billingsley
通讯作者: Patrick Billingsley