Kolmogorov-Arnold Network for Satellite Image Classification in Remote Sensing

TL;DR

This paper introduces the Kolmogorov-Arnold Network (KAN) integrated with pre-trained CNNs for remote sensing scene classification, demonstrating high accuracy and efficiency on the EuroSAT dataset, especially with ConvNeXt.

Contribution

The paper presents the first integration of KAN with various CNN models for satellite image classification, showing improved efficiency and competitive accuracy compared to traditional methods.

Findings

KAN achieves high accuracy with fewer epochs and parameters.

ConvNeXt + KAN reaches 94% accuracy in the first epoch.

KAN performs slightly better than MLP in later epochs.

Abstract

In this research, we propose the first approach for integrating the Kolmogorov-Arnold Network (KAN) with various pre-trained Convolutional Neural Network (CNN) models for remote sensing (RS) scene classification tasks using the EuroSAT dataset. Our novel methodology, named KCN, aims to replace traditional Multi-Layer Perceptrons (MLPs) with KAN to enhance classification performance. We employed multiple CNN-based models, including VGG16, MobileNetV2, EfficientNet, ConvNeXt, ResNet101, and Vision Transformer (ViT), and evaluated their performance when paired with KAN. Our experiments demonstrated that KAN achieved high accuracy with fewer training epochs and parameters. Specifically, ConvNeXt paired with KAN showed the best performance, achieving 94% accuracy in the first epoch, which increased to 96% and remained consistent across subsequent epochs. The results indicated that KAN and MLP both achieved similar accuracy, with KAN performing slightly better in later epochs. By utilizing the EuroSAT dataset, we provided a robust testbed to investigate whether KAN is suitable for remote sensing classification tasks. Given that KAN is a novel algorithm, there is substantial capacity for further development and optimization, suggesting that KCN offers a promising alternative for efficient image analysis in the RS field.