A Note on the Regularity of Images Generated by Convolutional Neural Networks

DOI10.1137/22M1525995zbMATH Open1521.65045arXiv2204.10588OpenAlexW4385071157MaRDI QIDQ6136232FDOQ6136232

M. Holler, Andreas Habring

Publication date: 29 August 2023

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Abstract: The regularity of images generated by convolutional neural networks, such as the U-net, generative networks, or the deep image prior, is analyzed. In a resolution-independent, infinite dimensional setting, it is shown that such images, represented as functions, are always continuous and, in some circumstances, even continuously differentiable, contradicting the widely accepted modeling of sharp edges in images via jump discontinuities. While such statements require an infinite dimensional setting, the connection to (discretized) neural networks used in practice is made by considering the limit as the resolution approaches infinity. As practical consequence, the results of this paper in particular provide analytical evidence that basic L2 regularization of network weights might lead to over-smoothed outputs.

Full work available at URL: https://arxiv.org/abs/2204.10588

zbMATH Keywords

machine learningfunctional analysisconvolutional neural networksmathematical imaging

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Numerical solutions of ill-posed problems in abstract spaces; regularization (65J20)

Cites Work

• A convex variational model for learning convolutional image atoms from incomplete data
• Nonlinear total variation based noise removal algorithms
• Title not available (Why is that?)
• Title not available (Why is that?)
• Functional analysis, Sobolev spaces and partial differential equations
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• A First Course in Sobolev Spaces
• Linear functional analysis. An application-oriented introduction. Translated from the 6th German edition by Robert Nürnberg
• Are natural images of bounded variation?
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Mathematical image processing. Translated from the German
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• A Generative Variational Model for Inverse Problems in Imaging
• Solving inverse problems using data-driven models
• Deep synthesis network for regularizing inverse problems

Cited In (3)

• Image augmentation with conformal mappings for a convolutional neural network
• Continuous Generative Neural Networks: A Wavelet-Based Architecture in Function Spaces
• Neural-network-based regularization methods for inverse problems in imaging

   Recommendations

• Regularization by architecture: a deep prior approach for inverse problems 👍 👎
• Big in Japan: regularizing networks for solving inverse problems 👍 👎
• Approximation properties of deep ReLU CNNs 👍 👎
• Lipschitz properties for deep convolutional networks 👍 👎
• A Generative Variational Model for Inverse Problems in Imaging 👍 👎

This page was built for publication: A Note on the Regularity of Images Generated by Convolutional Neural Networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6136232)