2021/03/29 by Fei Yang, Yang, Fei, Luis Herranz +6 · 6 citations
Computer Science · Engineering · #Advanced Data Compression Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Generative Adversarial Networks and Image Synthesis #Image and Signal Denoising Methods #Image and Video Processing (eess.IV) #cs.CV #eess.IV #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2103.15726
Accepted to CVPR 2021
openalex publication_date 2021/03/29 · arxiv created 2022/05/02 · arxiv updated 2022/05/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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 SlimCAEs 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.