Quantum Implicit Neural Compression

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fujihashi, Takuya, Koike-Akino, Toshiaki
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912170569105408
author Fujihashi, Takuya
Koike-Akino, Toshiaki
author_facet Fujihashi, Takuya
Koike-Akino, Toshiaki
contents Signal compression based on implicit neural representation (INR) is an emerging technique to represent multimedia signals with a small number of bits. While INR-based signal compression achieves high-quality reconstruction for relatively low-resolution signals, the accuracy of high-frequency details is significantly degraded with a small model. To improve the compression efficiency of INR, we introduce quantum INR (quINR), which leverages the exponentially rich expressivity of quantum neural networks for data compression. Evaluations using some benchmark datasets show that the proposed quINR-based compression could improve rate-distortion performance in image compression compared with traditional codecs and classic INR-based coding methods, up to 1.2dB gain.
format Preprint
id arxiv_https___arxiv_org_abs_2412_19828
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Quantum Implicit Neural Compression
Fujihashi, Takuya
Koike-Akino, Toshiaki
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Quantum Algebra
Signal compression based on implicit neural representation (INR) is an emerging technique to represent multimedia signals with a small number of bits. While INR-based signal compression achieves high-quality reconstruction for relatively low-resolution signals, the accuracy of high-frequency details is significantly degraded with a small model. To improve the compression efficiency of INR, we introduce quantum INR (quINR), which leverages the exponentially rich expressivity of quantum neural networks for data compression. Evaluations using some benchmark datasets show that the proposed quINR-based compression could improve rate-distortion performance in image compression compared with traditional codecs and classic INR-based coding methods, up to 1.2dB gain.
title Quantum Implicit Neural Compression
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Quantum Algebra
url https://arxiv.org/abs/2412.19828