Multi-scale gridded Gabor attention for cirrus segmentation

TL;DR

This paper introduces a multi-scale gridded Gabor attention mechanism that efficiently captures global context and texture orientation for improved segmentation of large astronomical dust clouds.

Contribution

It proposes a novel gridded attention method that reduces computational cost and enhances texture sensitivity, specifically tailored for large-scale image segmentation tasks.

Findings

Effective segmentation of dust clouds in astronomical images

Significant reduction in computational complexity

Enhanced texture orientation sensitivity

Abstract

In this paper, we address the challenge of segmenting global contaminants in large images. The precise delineation of such structures requires ample global context alongside understanding of textural patterns. CNNs specialise in the latter, though their ability to generate global features is limited. Attention measures long range dependencies in images, capturing global context, though at a large computational cost. We propose a gridded attention mechanism to address this limitation, greatly increasing efficiency by processing multi-scale features into smaller tiles. We also enhance the attention mechanism for increased sensitivity to texture orientation, by measuring correlations across features dependent on different orientations, in addition to channel and positional attention. We present results on a new dataset of astronomical images, where the task is segmenting large contaminating dust clouds.