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

03/04/2022
by   A. Burakhan Koyuncu, et al.
0

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, a.k.a. 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 image dataset. Our experimental results show that the proposed model provides up to 10 Model (VTM) 9.1, and outperforms various learning-based models.

READ FULL TEXT

page 2

page 4

research
06/25/2023

Efficient Contextformer: Spatio-Channel Window Attention for Fast Context Modeling in Learned Image Compression

In this work, we introduce Efficient Contextformer (eContextformer) for ...
research
08/30/2022

Learned Lossless Image Compression With Combined Autoregressive Models And Attention Modules

Lossless image compression is an essential research field in image compr...
research
09/19/2023

Multi-Context Dual Hyper-Prior Neural Image Compression

Transform and entropy models are the two core components in deep image c...
research
03/16/2022

The Devil Is in the Details: Window-based Attention for Image Compression

Learned image compression methods have exhibited superior rate-distortio...
research
11/19/2020

Latent-Separated Global Prediction for Learned Image Compression

Over the past several years, we have witnessed the impressive progress o...
research
03/30/2022

Practical Learned Lossless JPEG Recompression with Multi-Level Cross-Channel Entropy Model in the DCT Domain

JPEG is a popular image compression method widely used by individuals, d...
research
07/17/2020

Channel-wise Autoregressive Entropy Models for Learned Image Compression

In learning-based approaches to image compression, codecs are developed ...

Please sign up or login with your details

Forgot password? Click here to reset