DeepAI AI Chat
Log In Sign Up

Controlling Neural Networks via Energy Dissipation

by   Michael Moeller, et al.

The last decade has shown a tremendous success in solving various computer vision problems with the help of deep learning techniques. Lately, many works have demonstrated that learning-based approaches with suitable network architectures even exhibit superior performance for the solution of (ill-posed) image reconstruction problems such as deblurring, super-resolution, or medical image reconstruction. The drawback of purely learning-based methods, however, is that they cannot provide provable guarantees for the trained network to follow a given data formation process during inference. In this work we propose energy dissipating networks that iteratively compute a descent direction with respect to a given cost function or energy at the currently estimated reconstruction. Therefore, an adaptive step size rule such as a line-search, along with a suitable number of iterations can guarantee the reconstruction to follow a given data formation model encoded in the energy to arbitrary precision, and hence control the model's behavior even during test time. We prove that under standard assumptions, descent using the direction predicted by the network converges (linearly) to the global minimum of the energy. We illustrate the effectiveness of the proposed approach in experiments on single image super resolution and computed tomography (CT) reconstruction, and further illustrate extensions to convex feasibility problems.


Ultra Sharp : Study of Single Image Super Resolution using Residual Dense Network

For years, Single Image Super Resolution (SISR) has been an interesting ...

Deep Networks for Image Super-Resolution with Sparse Prior

Deep learning techniques have been successfully applied in many areas of...

Super-Resolution Image Reconstruction Based on Self-Calibrated Convolutional GAN

With the effective application of deep learning in computer vision, brea...

Deep Artifact-Free Residual Network for Single Image Super-Resolution

Recently, convolutional neural networks have shown promising performance...

On the inverse Potts functional for single-image super-resolution problems

We consider a variational model for single-image super-resolution based ...

Deep Adaptive Inference Networks for Single Image Super-Resolution

Recent years have witnessed tremendous progress in single image super-re...

Image Reconstruction with Predictive Filter Flow

We propose a simple, interpretable framework for solving a wide range of...