DeepAI AI Chat
Log In Sign Up

Convolutional Neural Networks Analyzed via Inverse Problem Theory and Sparse Representations

by   Cem Tarhan, et al.
Middle East Technical University

Inverse problems in imaging such as denoising, deblurring, superresolution (SR) have been addressed for many decades. In recent years, convolutional neural networks (CNNs) have been widely used for many inverse problem areas. Although their indisputable success, CNNs are not mathematically validated as to how and what they learn. In this paper, we prove that during training, CNN elements solve for inverse problems which are optimum solutions stored as CNN neuron filters. We discuss the necessity of mutual coherence between CNN layer elements in order for a network to converge to the optimum solution. We prove that required mutual coherence can be provided by the usage of residual learning and skip connections. We have set rules over training sets and depth of networks for better convergence, i.e. performance.


page 1

page 2

page 3

page 4


When to Use Convolutional Neural Networks for Inverse Problems

Reconstruction tasks in computer vision aim fundamentally to recover an ...

Regularizing linear inverse problems with convolutional neural networks

Deep convolutional neural networks trained on large datsets have emerged...

Stability properties for a class of inverse problems

We establish Lipschitz stability properties for a class of inverse probl...

Deep Convolutional Neural Network for Inverse Problems in Imaging

In this paper, we propose a novel deep convolutional neural network (CNN...

Noise2Inverse: Self-supervised deep convolutional denoising for linear inverse problems in imaging

Recovering a high-quality image from noisy indirect measurement is an im...

Boosting CNN beyond Label in Inverse Problems

Convolutional neural networks (CNN) have been extensively used for inver...

Deep learning for inverse problems with unknown operator

We consider ill-posed inverse problems where the forward operator T is u...