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.
|Title of host publication||MM 2020 - Proceedings of the 28th ACM International Conference on Multimedia|
|Publisher||Association for Computing Machinery, Inc|
|Number of pages||9|
|Publication status||Published - 2020 Oct 12|
|Event||28th ACM International Conference on Multimedia, MM 2020 - Virtual, Online, United States|
Duration: 2020 Oct 12 → 2020 Oct 16
|Name||MM 2020 - Proceedings of the 28th ACM International Conference on Multimedia|
|Conference||28th ACM International Conference on Multimedia, MM 2020|
|Period||20/10/12 → 20/10/16|
Bibliographical notePublisher Copyright:
© 2020 ACM.
All Science Journal Classification (ASJC) codes
- Computer Graphics and Computer-Aided Design
- Human-Computer Interaction