arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.11225cs.LG
收藏

学习框架中的小波设计

Wavelet Design in a Learning Framework

Indian Institute of Science(印度科学学院);Rice University(莱斯大学)

Dhruv Jawali, Abhishek Kumar, Chandra Sekhar Seelamantula

摘要:

已经证明,小波变换在若干信号和图像处理应用中是非常成功的。小波设计已经是一个活跃的研究领域超过二十年,与问题往往是从分析的角度来处理。在本文中,我们介绍了一种基于学习的小波设计方法。我们绘制了卷积自动编码器和小波多分辨率近似之间的平行,并展示了学习角度如何提供一个连贯的计算框架来解决设计问题。我们的目标是通过训练滤波器组自动编码器来设计与数据无关的小波,这排除了对定制数据集的需求。事实上,我们使用高维高斯向量来训练滤波器组自动编码器,并表明接近零的训练损失意味着学习的滤波器以非常高的概率满足完美的重建特性。小波的性质,如正交性,紧支持,平滑性,对称性和消失的时刻,可以通过适当地设计自动编码器架构,并与一个合适的正则化项添加到学习过程中使用的均方误差成本。我们的方法不仅恢复了著名的Daubechies族的正交小波和对称双正交小波的Cohen-Daubechies-Feauveau族,但也学习这些家庭以外的小波。

英文摘要:

Wavelets have proven to be highly successful in several signal and image processing applications. Wavelet design has been an active field of research for over two decades, with the problem often being approached from an analytical perspective. In this paper, we introduce a learning based approach to wavelet design. We draw a parallel between convolutional autoencoders and wavelet multiresolution approximation, and show how the learning angle provides a coherent computational framework for addressing the design problem. We aim at designing data-independent wavelets by training filterbank autoencoders, which precludes the need for customized datasets. In fact, we use high-dimensional Gaussian vectors for training filterbank autoencoders, and show that a near-zero training loss implies that the learnt filters satisfy the perfect reconstruction property with very high probability. Properties of a wavelet such as orthogonality, compact support, smoothness, symmetry, and vanishing moments can be incorporated by designing the autoencoder architecture appropriately and with a suitable regularization term added to the mean-squared error cost used in the learning process. Our approach not only recovers the well known Daubechies family of orthogonal wavelets and the Cohen-Daubechies-Feauveau family of symmetric biorthogonal wavelets, but also learns wavelets outside these families.

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。

↑