Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compression

Abstract

Entropy modeling is a key component for high-performance image compression algorithms. Recent developments in autoregressive context modeling helped learning-based methods to surpass their classical counterparts. However, the performance of those models can be further improved due to the underexploited spatio-channel dependencies in latent space, and the suboptimal implementation of context adaptivity. Inspired by the adaptive characteristics of the transformers, we propose a transformer-based context model, named Contextformer, which generalizes the de facto standard attention mechanism to spatio-channel attention. We replace the context model of a modern compression framework with the Contextformer and test it on the widely used Kodak, CLIC2020, and Tecnick image datasets. Our experimental results show that the proposed model provides up to 11% rate savings compared to the standard Versatile Video Coding (VVC) Test Model (VTM) 16.2, and outperforms various learning-based models in terms of PSNR and MS-SSIM.

Accepted at ECCV 2022; 31 pages (14 main paper + References + 13 Appendix)

Cited by in corpus (7)

• MLIC: Multi-Reference Entropy Model for Learned Image Compression
• MLIC++: Linear Complexity Multi-Reference Entropy Modeling for Learned Image Compression
• GroupedMixer: An Entropy Model with Group-wise Token-Mixers for Learned Image Compression
• Controlling Rate, Distortion, and Realism: Towards a Single Comprehensive Neural Image Compression Model
• LLIC: Large Receptive Field Transform Coding with Adaptive Weights for Learned Image Compression
• Window-based Channel Attention for Wavelet-enhanced Learned Image Compression
• Overview of Variable Rate Coding in JPEG AI