Out of distribution evaluation for neural image compression

RESOURCE

Abstract

Official code for the NeurIPS 2023 paper "Neural Image Compression: Generalization, Robustness, and Spectral Biases". This code can be used to: - Computing spectral distortion errors of images compressed with traditional codes or neural image compression models (as proposed in the aformentioned paper) - Visualize power spectral densities and fourier heatmaps (as proposed in the aformentioned paper) - Train and test a variety of neural image compression models
Developers:
Lieberman, Kelsey [1]
  1. Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
Release Date:
2023-09-01
Project Type:
Open Source, Publicly Available Repository
Software Type:
Scientific
Version:
1.0
Licenses:
MIT License
Sponsoring Org.:
Code ID:
115924
Site Accession Number:
LLNL-CODE-856963
Research Org.:
Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
Country of Origin:
United States

RESOURCE

Citation Formats

Lieberman, Kelsey A. Out of distribution evaluation for neural image compression. Computer Software. https://github.com/klieberman/ood_nic. USDOE National Nuclear Security Administration (NNSA). 01 Sep. 2023. Web. doi:10.11578/dc.20231114.4.
Lieberman, Kelsey A. (2023, September 01). Out of distribution evaluation for neural image compression. [Computer software]. https://github.com/klieberman/ood_nic. https://doi.org/10.11578/dc.20231114.4.
Lieberman, Kelsey A. "Out of distribution evaluation for neural image compression." Computer software. September 01, 2023. https://github.com/klieberman/ood_nic. https://doi.org/10.11578/dc.20231114.4.
@misc{ doecode_115924,
title = {Out of distribution evaluation for neural image compression},
author = {Lieberman, Kelsey A.},
abstractNote = {Official code for the NeurIPS 2023 paper "Neural Image Compression: Generalization, Robustness, and Spectral Biases". This code can be used to: - Computing spectral distortion errors of images compressed with traditional codes or neural image compression models (as proposed in the aformentioned paper) - Visualize power spectral densities and fourier heatmaps (as proposed in the aformentioned paper) - Train and test a variety of neural image compression models},
doi = {10.11578/dc.20231114.4},
url = {https://doi.org/10.11578/dc.20231114.4},
howpublished = {[Computer Software] \url{https://doi.org/10.11578/dc.20231114.4}},
year = {2023},
month = {sep}
}