Information Bottleneck Measurement for Compressed Sensing Image Reconstruction

Bokyeung Lee, Kyungdeuk Ko, Jonghwan Hong, Bonhwa Ku, Hanseok Ko

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)


Image Compressed Sensing (CS) has achieved a lot of performance improvement thanks to advances in deep networks. The CS method is generally composed of a sensing and a decoder. The sensing and decoder networks have a significant impact on the reconstruction performance, and it is obvious that both two networks must be in harmony. However, previous studies have focused on designing the loss function considering only the decoder network. In this paper, we propose a novel training process that can learn sensing and decoder networks simultaneously using Information Bottleneck (IB) theory. By maximizing importance through proposed importance generator, the sensing network is trained to compress important information for image reconstruction of the decoder network. The representative experimental results demonstrate that the proposed method is applied in recently proposed CS algorithms and increases the reconstruction performance with large margin in all CS ratios.

Original languageEnglish
Pages (from-to)1943-1947
Number of pages5
JournalIEEE Signal Processing Letters
Publication statusPublished - 2022

Bibliographical note

Publisher Copyright:
© 1994-2012 IEEE.


  • Information bottleneck
  • deep learning
  • image compressed sens- ing

ASJC Scopus subject areas

  • Signal Processing
  • Applied Mathematics
  • Electrical and Electronic Engineering


Dive into the research topics of 'Information Bottleneck Measurement for Compressed Sensing Image Reconstruction'. Together they form a unique fingerprint.

Cite this