Band Selection from Hyperspectral Images Using Attention-based Convolutional Neural Networks

TL;DR

This paper proposes attention-based convolutional neural networks for hyperspectral band selection, effectively identifying key spectral regions and enabling the creation of compact, informative feature sets with high classification accuracy.

Contribution

Introduces modular attention mechanisms within CNNs for hyperspectral band selection, allowing end-to-end training and improved identification of significant spectral bands.

Findings

High classification accuracy achieved with attention-based models

Effective selection of compact, meaningful spectral bands

Models consistently identify significant bands in training data

Abstract

This paper introduces new attention-based convolutional neural networks for selecting bands from hyperspectral images. The proposed approach re-uses convolutional activations at different depths, identifying the most informative regions of the spectrum with the help of gating mechanisms. Our attention techniques are modular and easy to implement, and they can be seamlessly trained end-to-end using gradient descent. Our rigorous experiments showed that deep models equipped with the attention mechanism deliver high-quality classification, and repeatedly identify significant bands in the training data, permitting the creation of refined and extremely compact sets that retain the most meaningful features.