AMBER -- Advanced SegFormer for Multi-Band Image Segmentation: an application to Hyperspectral Imaging

TL;DR

AMBER is an advanced deep learning model based on SegFormer, designed for multi-band hyperspectral image segmentation, outperforming CNNs and achieving state-of-the-art results on multiple benchmark datasets.

Contribution

The paper introduces AMBER, a novel architecture that integrates 3D convolutions and a Funnelizer layer into SegFormer for direct hyperspectral data processing without spectral reduction.

Findings

AMBER outperforms CNN-based methods on benchmark datasets.

Achieves state-of-the-art results on the PRISMA dataset.

Demonstrates robustness and adaptability to airborne and spaceborne data.

Abstract

Deep learning has revolutionized the field of hyperspectral image (HSI) analysis, enabling the extraction of complex spectral and spatial features. While convolutional neural networks (CNNs) have been the backbone of HSI classification, their limitations in capturing global contextual features have led to the exploration of Vision Transformers (ViTs). This paper introduces AMBER, an advanced SegFormer specifically designed for multi-band image segmentation. AMBER enhances the original SegFormer by incorporating three-dimensional convolutions, custom kernel sizes, and a Funnelizer layer. This architecture enables processing hyperspectral data directly, without requiring spectral dimensionality reduction during preprocessing. Our experiments, conducted on three benchmark datasets (Salinas, Indian Pines, and Pavia University) and on a dataset from the PRISMA satellite, show that AMBER outperforms traditional CNN-based methods in terms of Overall Accuracy, Kappa coefficient, and Average Accuracy on the first three datasets, and achieves state-of-the-art performance on the PRISMA dataset. These findings highlight AMBER's robustness, adaptability to both airborne and spaceborne data, and its potential as a powerful solution for remote sensing and other domains requiring advanced analysis of high-dimensional data.