GABIC: Graph-based Attention Block for Image Compression

While standardized codecs like JPEG and HEVC-intra represent the industry standard in image compression, neural Learned Image Compression (LIC) codecs represent a promising alternative. In detail, integrating attention mechanisms from Vision Transformers into LIC models has shown improved compressio...

Full description

Saved in:

Bibliographic Details
Main Authors:	Spadaro, Gabriele, Presta, Alberto, Tartaglione, Enzo, Giraldo, Jhony H, Grangetto, Marco, Fiandrotti, Attilio
Format:	Journal Article
Language:	English
Published:	03-10-2024
Subjects:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Learning
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	While standardized codecs like JPEG and HEVC-intra represent the industry standard in image compression, neural Learned Image Compression (LIC) codecs represent a promising alternative. In detail, integrating attention mechanisms from Vision Transformers into LIC models has shown improved compression efficiency. However, extra efficiency often comes at the cost of aggregating redundant features. This work proposes a Graph-based Attention Block for Image Compression (GABIC), a method to reduce feature redundancy based on a k-Nearest Neighbors enhanced attention mechanism. Our experiments show that GABIC outperforms comparable methods, particularly at high bit rates, enhancing compression performance.
DOI:	10.48550/arxiv.2410.02981