arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1401.2804cs.CV
收藏

分析算子学习的见解:从基于补丁的稀疏模型到高阶MRF

Insights into analysis operator learning: From patch-based sparse models to higher-order MRFs

Graz University of Technology(格拉茨工业大学);National University of Defense Technology(国防科技大学)

Yunjin Chen, René Ranftl, Thomas Pock

摘要:

本文提出了一种新的学习算法最近推出的共同稀疏分析模型。首先,我们通过建立与基于过滤器的MRF模型(如Roth和Black的专家领域(FoE)模型)的连接,对共稀疏分析模型给出了新的见解。对于训练,我们引入了一种称为双层优化的技术来学习分析运算符。与现有的分析算子学习方法相比,我们的训练过程具有不受分析算子约束的优点。我们调查的影响,不同方面的共同稀疏分析模型,并表明,稀疏促进功能(也称为惩罚函数)是最重要的因素,在该模型中。为了证明我们的训练方法的有效性,我们将我们训练的模型应用于各种经典的图像复原问题。数值实验表明,我们训练的模型明显优于现有的分析算子学习方法,并与最先进的图像去噪算法相当。我们的方法开发了一个框架,是直观的理解和易于实施。

英文摘要:

This paper addresses a new learning algorithm for the recently introduced co-sparse analysis model. First, we give new insights into the co-sparse analysis model by establishing connections to filter-based MRF models, such as the Field of Experts (FoE) model of Roth and Black. For training, we introduce a technique called bi-level optimization to learn the analysis operators. Compared to existing analysis operator learning approaches, our training procedure has the advantage that it is unconstrained with respect to the analysis operator. We investigate the effect of different aspects of the co-sparse analysis model and show that the sparsity promoting function (also called penalty function) is the most important factor in the model. In order to demonstrate the effectiveness of our training approach, we apply our trained models to various classical image restoration problems. Numerical experiments show that our trained models clearly outperform existing analysis operator learning approaches and are on par with state-of-the-art image denoising algorithms. Our approach develops a framework that is intuitive to understand and easy to implement.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑