SRL-SOA: Self-Representation Learning with Sparse 1D-Operational Autoencoder for Hyperspectral Image Band Selection

TL;DR

This paper introduces SRL-SOA, a novel autoencoder-based framework for hyperspectral image band selection that learns sparse representations using shallow, 1D-operational layers, improving classification accuracy and reducing overfitting.

Contribution

The paper proposes a new Sparse 1D-Operational Autoencoder (SOA) within a self-representation learning framework for hyperspectral band selection, emphasizing shallow architecture and sparse representation.

Findings

Outperforms existing methods on Indian Pines and Salinas-A datasets

Achieves higher land cover classification accuracy

Demonstrates effective sparse representation learning

Abstract

The band selection in the hyperspectral image (HSI) data processing is an important task considering its effect on the computational complexity and accuracy. In this work, we propose a novel framework for the band selection problem: Self-Representation Learning (SRL) with Sparse 1D-Operational Autoencoder (SOA). The proposed SLR-SOA approach introduces a novel autoencoder model, SOA, that is designed to learn a representation domain where the data are sparsely represented. Moreover, the network composes of 1D-operational layers with the non-linear neuron model. Hence, the learning capability of neurons (filters) is greatly improved with shallow architectures. Using compact architectures is especially crucial in autoencoders as they tend to overfit easily because of their identity mapping objective. Overall, we show that the proposed SRL-SOA band selection approach outperforms the competing methods over two HSI data including Indian Pines and Salinas-A considering the achieved land cover classification accuracies. The software implementation of the SRL-SOA approach is shared publicly at https://github.com/meteahishali/SRL-SOA.