Learning-Based Image Compression With Parameter-Adaptive Rate-Constrained Loss

In recent years, the crucial task of image compression has been addressed by end-to-end neural network methods. However, achieving fine-grained rate control in this new paradigm has presented challenges. In our previous work, we explored mismatches in rate estimation during target-rate-oriented trai...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE signal processing letters Jg. 31; S. 1 - 5
Hauptverfasser: Guerin, Nilson D., da Silva, Renam Castro, Macchiavello, Bruno
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 01.01.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Adaptation models
convolutional neural network
Entropy
Estimation
Image coding
Image compression
learning-based image compression
Neural networks
Noise
Parameters
Quantization (signal)
rate control
Training
variational autoencoder
ISSN:1070-9908, 1558-2361
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In recent years, the crucial task of image compression has been addressed by end-to-end neural network methods. However, achieving fine-grained rate control in this new paradigm has presented challenges. In our previous work, we explored mismatches in rate estimation during target-rate-oriented training and proposed heuristics involving costly parameter searches as a solution. This work proposes a lightweight approach, which dynamically adapts loss parameters to mitigate rate estimation issues, ensuring precise target rate attainment. Inspired by Reinforcement Learning, our method exhibits performance comparable to preceding approaches on the Kodak dataset in terms of PSNR. Additionally, it reduces computational training costs.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1070-9908
1558-2361
DOI:10.1109/LSP.2024.3383801