Efficient Fine-Tuning of Neural Networks for Artifact Removal in Deep Learning for Inverse Imaging Problems

Alice Lucas, Santiago Lopez-Tapia, Rafael Molina, Aggelos K. Katsaggelos

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

While Deep Neural Networks trained for solving inverse imaging problems (such as super-resolution, denoising, or inpainting tasks) regularly achieve new state-of-the-art restoration performance, this increase in performance is often accompanied with undesired artifacts generated in their solution. These artifacts are usually specific to the type of neural network architecture, training, or test input image used for the inverse imaging problem at hand. In this paper, we propose a fast, efficient post-processing method for reducing these artifacts. Given a test input image and its known image formation model, we fine-tune the parameters of the trained network and iteratively update them using a data consistency loss. We show that in addition to being efficient and applicable to large variety of problems, our post-processing through fine-tuning approach enhances the solution originally provided by the neural network by maintaining its restoration quality while reducing the observed artifacts, as measured qualitatively and quantitatively.

Original languageEnglish (US)
Title of host publication2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings
PublisherIEEE Computer Society
Pages3591-3595
Number of pages5
ISBN (Electronic)9781538662496
DOIs
StatePublished - Sep 2019
Event26th IEEE International Conference on Image Processing, ICIP 2019 - Taipei, Taiwan, Province of China
Duration: Sep 22 2019Sep 25 2019

Publication series

NameProceedings - International Conference on Image Processing, ICIP
Volume2019-September
ISSN (Print)1522-4880

Conference

Conference26th IEEE International Conference on Image Processing, ICIP 2019
Country/TerritoryTaiwan, Province of China
CityTaipei
Period9/22/199/25/19

Keywords

  • Artifacts
  • Data Consistency
  • Deep Neural Networks
  • Fine-tuning
  • Image and Video Processing
  • Inversion

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Fingerprint

Dive into the research topics of 'Efficient Fine-Tuning of Neural Networks for Artifact Removal in Deep Learning for Inverse Imaging Problems'. Together they form a unique fingerprint.

Cite this