A Benchmark Study of Neural Network Compression Methods for Hyperspectral Image Classification

TL;DR

This paper systematically evaluates neural network compression techniques—pruning, quantization, and knowledge distillation—for hyperspectral image classification, demonstrating significant efficiency gains with minimal accuracy loss.

Contribution

It provides a comprehensive comparison of compression methods on hyperspectral datasets, offering insights into their trade-offs and practical deployment in remote sensing.

Findings

Compressed models reduce size and computation significantly.

Maintained competitive classification accuracy.

Insights into trade-offs between efficiency and accuracy.

Abstract

Deep neural networks have achieved strong performance in image classification tasks due to their ability to learn complex patterns from high-dimensional data. However, their large computational and memory requirements often limit deployment on resource-constrained platforms such as remote sensing devices and edge systems. Network compression techniques have therefore been proposed to reduce model size and computational cost while maintaining predictive performance. In this study, we conduct a systematic evaluation of neural network compression methods for a remote sensing application, namely hyperspectral land cover classification. Specifically, we examine three widely used compression strategies for convolutional neural networks: pruning, quantization, and knowledge distillation. Experiments are conducted on two benchmark hyperspectral datasets, considering classification accuracy, memory consumption, and inference efficiency. Our results demonstrate that compressed models can significantly reduce model size and computational cost while maintaining competitive classification performance. These findings provide insights into the trade-offs between compression ratio, efficiency, and accuracy, and highlight the potential of compression techniques for enabling efficient deep learning deployment in remote sensing applications.