Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compression
arXiv:2203.02452 · doi:10.1007/978-3-031-19800-7_26
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.
arXiv commentAccepted at ECCV 2022; 31 pages (14 main paper + References + 13 Appendix)
References in corpus (7)
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Video Enhancement with Task-Oriented Flow
- Neural Image Compression via Non-Local Attention Optimization and Improved Context Modeling
- Non-local Attention Optimized Deep Image Compression
- Causal Contextual Prediction for Learned Image Compression
- Efficient and Effective Context-Based Convolutional Entropy Modeling for Image Compression
- Learning Accurate Entropy Model with Global Reference for Image Compression
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