Instability of Successive Deep Image Compression

Jun-Hyuk Kim, Soobeom Jang, Jun-Ho Choi, Jong-Seok LeeACM Multimedia 2020 · OpenReview

Abstract

Successive image compression refers to the process of repeated encoding and decoding of an image. It frequently occurs during sharing, manipulation, and re-distribution of images. While deep learning-based methods have made significant progress for single-step compression, thorough analysis of their performance under successive compression has not been conducted. In this paper, we conduct comprehensive analysis of successive deep image compression. First, we introduce a new observation, instability of successive deep image compression, which is not observed in JPEG, and discuss causes of the instability. Then, we conduct a successive image compression benchmark for the state-of-the-art deep learning-based methods, and analyze the factors that affect the instability in a comparative manner. Finally, we propose a new loss function for training deep compression models, called feature identity loss, to mitigate the instability of successive deep image compression.
BibTeX
@inproceedings{kim2020instability,
  author = {Jun-Hyuk Kim and Soobeom Jang and Jun-Ho Choi and Jong-Seok Lee},
  title = {{Instability of Successive Deep Image Compression}},
  booktitle = {ACM Multimedia},
  year = {2020},
  url = {https://openreview.net/forum?id=qlsev8QlMW},
}

Loading related content...

Figure