Slimmable Compressive Autoencoders for Practical Neural Image Compression

Neural image compression leverages deep neural networks to outperform traditional image codecs in rate-distortion performance. However, the resulting models are also heavy, computationally demanding and generally optimized for a single rate, limiting their practical use. Focusing on practical image...

Full description

Saved in:
Bibliographic Details
Published inProceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 4996 - 5005
Main Authors Yang, Fei, Herranz, Luis, Cheng, Yongmei, Mozerov, Mikhail G.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2021
Subjects
Adaptation models
Computational modeling
Image coding
Performance evaluation
Rate-distortion
Transform coding
Video coding
Online AccessGet full text
ISSN1063-6919
DOI10.1109/CVPR46437.2021.00496

Cover

More Information
Summary:Neural image compression leverages deep neural networks to outperform traditional image codecs in rate-distortion performance. However, the resulting models are also heavy, computationally demanding and generally optimized for a single rate, limiting their practical use. Focusing on practical image compression, we propose slimmable compressive autoencoders (SlimCAEs), where rate (R) and distortion (D) are jointly optimized for different capacities. Once trained, encoders and decoders can be executed at different capacities, leading to different rates and complexities. We show that a successful implementation of Slim-CAEs requires suitable capacity-specific RD tradeoffs. Our experiments show that SlimCAEs are highly flexible models that provide excellent rate-distortion performance, variable rate, and dynamic adjustment of memory, computational cost and latency, thus addressing the main requirements of practical image compression.
ISSN:1063-6919
DOI:10.1109/CVPR46437.2021.00496