Towards Analyzing the Robustness of Deep Light-weight Image Super Resolution Networks under Distribution Shift

Alireza Esmaeilzehi, Lei Ma, M. Omair Ahmad

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

Abstract

Deep light-weight image super resolution networks that provide a high performance have numerous real-life applications, such as mobile devices and multimedia systems. Hence, analyzing the capability of such deep networks in providing a similar performance between the cases that they are applied to the images with and without distributions similar to that of the training is crucial. In this paper, we carry out the robustness analysis of the deep state-of-the-art light-weight super resolution networks by proposing and using three metrics that are based on the statistical information of the super resolved images in both pixel level and feature level. The results of our metrics for the deep state-of-the-art light-weight super resolution networks demonstrate the behavior of such networks against realistic distribution shift in the test dataset.

Original languageEnglish
Title of host publication2022 IEEE 24th International Workshop on Multimedia Signal Processing, MMSP 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665471893
DOIs
Publication statusPublished - 2022
Event24th IEEE International Workshop on Multimedia Signal Processing, MMSP 2022 - Shanghai, China
Duration: Sept 26 2022Sept 28 2022

Publication series

Name2022 IEEE 24th International Workshop on Multimedia Signal Processing, MMSP 2022

Conference

Conference24th IEEE International Workshop on Multimedia Signal Processing, MMSP 2022
Country/TerritoryChina
CityShanghai
Period9/26/229/28/22

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Media Technology

Fingerprint

Dive into the research topics of 'Towards Analyzing the Robustness of Deep Light-weight Image Super Resolution Networks under Distribution Shift'. Together they form a unique fingerprint.

Cite this