The sibling neural estimator: Improving iterative image decoding with gradient communication

Ankur Mali, Alexander G. Ororbia, C. Lee Giles

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


For lossy image compression, we develop a neural-based system which learns a nonlinear estimator for decoding from quantized representations. The system links two recurrent networks that 'help' each other reconstruct the same target image patches using complementary portions of the spatial context, communicating with each other via gradient signals. This dual agent system builds upon prior work that proposed an iterative refinement algorithm for recurrent neural network (RNN) based decoding. Our approach works with any neural or non-neural encoder. Our system progressively reduces image patch reconstruction error over a fixed number of steps. Experiments with variations of RNN memory cells show that our system consistently creates lower distortion images of higher perceptual quality compared to other approaches. Specifically, on the Kodak Lossless True Color Image Suite, we observe gains of 1:64 decibel (dB) over JPEG, a 1:46 dB over JPEG2000, a 1:34 dB over the GOOG neural baseline, 0:36 over E2E (a modern competitive neural compression model), and 0:37 over a single iterative neural decoder.

Original languageEnglish (US)
Title of host publicationProceedings - DCC 2020
Subtitle of host publicationData Compression Conference
EditorsAli Bilgin, Michael W. Marcellin, Joan Serra-Sagrista, James A. Storer
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages10
ISBN (Electronic)9781728164571
StatePublished - Mar 2020
Event2020 Data Compression Conference, DCC 2020 - Snowbird, United States
Duration: Mar 24 2020Mar 27 2020

Publication series

NameData Compression Conference Proceedings
ISSN (Print)1068-0314


Conference2020 Data Compression Conference, DCC 2020
Country/TerritoryUnited States

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications


Dive into the research topics of 'The sibling neural estimator: Improving iterative image decoding with gradient communication'. Together they form a unique fingerprint.

Cite this