Terrain Classification using Transfer Learning on Hyperspectral Images: A Comparative study

TL;DR

This paper explores transfer learning with deep neural networks for hyperspectral image classification, demonstrating reduced training time and comparable accuracy compared to traditional training methods, through a comparative analysis of CNN and MLP models.

Contribution

It introduces a transfer learning approach for hyperspectral image classification that reduces training time and dependence on large labeled datasets, with a detailed comparison of CNN and MLP architectures.

Findings

Transfer learning significantly reduces training time.

Scaling layers can cause overfitting without accuracy gains.

Transfer learning maintains accuracy while decreasing training time.

Abstract

A Hyperspectral image contains much more number of channels as compared to a RGB image, hence containing more information about entities within the image. The convolutional neural network (CNN) and the Multi-Layer Perceptron (MLP) have been proven to be an effective method of image classification. However, they suffer from the issues of long training time and requirement of large amounts of the labeled data, to achieve the expected outcome. These issues become more complex while dealing with hyperspectral images. To decrease the training time and reduce the dependence on large labeled dataset, we propose using the method of transfer learning. The hyperspectral dataset is preprocessed to a lower dimension using PCA, then deep learning models are applied to it for the purpose of classification. The features learned by this model are then used by the transfer learning model to solve a new classification problem on an unseen dataset. A detailed comparison of CNN and multiple MLP architectural models is performed, to determine an optimum architecture that suits best the objective. The results show that the scaling of layers not always leads to increase in accuracy but often leads to overfitting, and also an increase in the training time.The training time is reduced to greater extent by applying the transfer learning approach rather than just approaching the problem by directly training a new model on large datasets, without much affecting the accuracy.