Device Interoperability for Learned Image Compression with Weights and Activations Quantization

Learning-based image compression has improved to a level where it can outperform traditional image codecs such as HEVC and VVC in terms of coding performance. In addition to good compression performance, device interoperability is essential for a compression codec to be deployed, i.e., encoding and...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Picture Coding Symposium S. 151 - 155
Hauptverfasser: Koyuncu, Esin, Solovyev, Timofey, Alshina, Elena, Kaup, Andre
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 07.12.2022
Schlagworte:
Codecs
Decoding
device interoperability
Entropy
Image coding
Interoperability
learning-based image compression
neural network quantization
Performance evaluation
Quantization (signal)
ISSN:2472-7822
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Learning-based image compression has improved to a level where it can outperform traditional image codecs such as HEVC and VVC in terms of coding performance. In addition to good compression performance, device interoperability is essential for a compression codec to be deployed, i.e., encoding and decoding on different CPUs or GPUs should be error-free and with negligible performance reduction. In this paper, we present a method to solve the device interoperability problem of a state-of-the-art image compression network. We implement quantization to entropy networks which output entropy parameters. We suggest a simple method which can ensure cross-platform encoding and decoding, and can be implemented quickly with minor performance deviation, of 0.3% BD-rate, from floating point model results.
ISSN:2472-7822
DOI:10.1109/PCS56426.2022.10018040