MEMORY-EFFICIENT LEARNED IMAGE COMPRESSION WITH PRUNED HYPERPRIOR MODULE

Ao Luo, Heming Sun*, Jinming Liu, Jiro Katto

*Corresponding author for this work

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

3 Citations (Scopus)

Abstract

Learned Image Compression (LIC) gradually became more and more famous in these years. The hyperprior-module-based LIC models have achieved remarkable rate-distortion performance. However, the memory cost of these LIC models is too large to actually apply them to various devices, especially to portable or edge devices. The parameter scale is directly linked with memory cost. In our research, we found the hyperprior module is not only highly over-parameterized, but also its latent representation contains redundant information. Therefore, we propose a novel pruning method named ERHP in this paper to efficiently reduce the memory cost of hyperprior module, while improving the network performance. The experiments show our method is effective, reducing at least 22.6% parameters in the whole model while achieving better rate-distortion performance.

Original languageEnglish
Title of host publication2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings
PublisherIEEE Computer Society
Pages3061-3065
Number of pages5
ISBN (Electronic)9781665496209
DOIs
Publication statusPublished - 2022
Event29th IEEE International Conference on Image Processing, ICIP 2022 - Bordeaux, France
Duration: 2022 Oct 162022 Oct 19

Publication series

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

Conference

Conference29th IEEE International Conference on Image Processing, ICIP 2022
Country/TerritoryFrance
CityBordeaux
Period22/10/1622/10/19

Keywords

  • Hyperprior Module
  • Learned Image Compression
  • Model Pruning

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Fingerprint

Dive into the research topics of 'MEMORY-EFFICIENT LEARNED IMAGE COMPRESSION WITH PRUNED HYPERPRIOR MODULE'. Together they form a unique fingerprint.

Cite this