Training compression artifacts reduction network with domain adaptation

Yu Jin Ham, Chaehwa Yoo, Je Won Kang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations


Compression artifact removal is imperative for more visually pleasing contents after image and video compression. Recent works on compression artifact reduction network (CARN) assume that the same or similar quality of images would be employed for both training and testing, and, accordingly, a model needs a quality factor as a prior to accomplish the task successfully. However, the possible discrepancy will degrade performance substantially in a target if the model confronts a different level of distortion from the training phase. To solve the problem, we propose a novel training scheme of CARN to take an advantage of domain adaptation (DA). Specifically, we assign an image encoded with a different quality factor as a different domain and train a CARN using DA to perform robustly in another domain of a different level of distortion. Experimental results demonstrate that the proposed method achieves superior performance on DIV2K, BSD68, and Set12.

Original languageEnglish
Title of host publicationApplications of Digital Image Processing XLIV
EditorsAndrew G. Tescher, Touradj Ebrahimi
ISBN (Electronic)9781510645226
StatePublished - 2021
EventApplications of Digital Image Processing XLIV 2021 - San Diego, United States
Duration: 1 Aug 20215 Aug 2021

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X


ConferenceApplications of Digital Image Processing XLIV 2021
Country/TerritoryUnited States
CitySan Diego

Bibliographical note

Funding Information:
This research was supported by the MSIT(Ministry of Science and ICT), Korea, under the ITRC(Information Technology Research Center) support program(IITP–2021–2020–0–01460) supervised by the IITP(Institute for Information & Communications Technology Planning & Evaluation)

Publisher Copyright:
© COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.


  • Compression Artifact Reduction
  • Deep Learning
  • Domain Adaptation
  • Video/Image Coding


Dive into the research topics of 'Training compression artifacts reduction network with domain adaptation'. Together they form a unique fingerprint.

Cite this