Convolutional Transformer-Based Image Compression

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Arezki, Bouzid, Feng, Fangchen, Mokraoui, Anissa
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929489743708160
author Arezki, Bouzid
Feng, Fangchen
Mokraoui, Anissa
author_facet Arezki, Bouzid
Feng, Fangchen
Mokraoui, Anissa
contents In this paper, we present a novel transformer-based architecture for end-to-end image compression. Our architecture incorporates blocks that effectively capture local dependencies between tokens, eliminating the need for positional encoding by integrating convolutional operations within the multi-head attention mechanism. We demonstrate through experiments that our proposed framework surpasses state-of-the-art CNN-based architectures in terms of the trade-off between bit-rate and distortion and achieves comparable results to transformer-based methods while maintaining lower computational complexity.
format Preprint
id arxiv_https___arxiv_org_abs_2409_04118
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Convolutional Transformer-Based Image Compression
Arezki, Bouzid
Feng, Fangchen
Mokraoui, Anissa
Image and Video Processing
In this paper, we present a novel transformer-based architecture for end-to-end image compression. Our architecture incorporates blocks that effectively capture local dependencies between tokens, eliminating the need for positional encoding by integrating convolutional operations within the multi-head attention mechanism. We demonstrate through experiments that our proposed framework surpasses state-of-the-art CNN-based architectures in terms of the trade-off between bit-rate and distortion and achieves comparable results to transformer-based methods while maintaining lower computational complexity.
title Convolutional Transformer-Based Image Compression
topic Image and Video Processing
url https://arxiv.org/abs/2409.04118