Land Cover and Land Use Detection using Semi-Supervised Learning

TL;DR

This paper introduces a semi-supervised learning approach for remote sensing land cover and land use detection that creates artificial labels, addresses class imbalance, and outperforms existing methods on multiple datasets.

Contribution

The paper proposes a novel semi-supervised learning method that uses artificial labels and class resampling to improve accuracy and reduce bias in land cover detection.

Findings

Outperforms MSMatch and FixMatch on UCM and EuroSAT datasets

Reduces labeled data requirements significantly

Addresses class imbalance and model bias effectively

Abstract

Semi-supervised learning (SSL) has made significant strides in the field of remote sensing. Finding a large number of labeled datasets for SSL methods is uncommon, and manually labeling datasets is expensive and time-consuming. Furthermore, accurately identifying remote sensing satellite images is more complicated than it is for conventional images. Class-imbalanced datasets are another prevalent phenomenon, and models trained on these become biased towards the majority classes. This becomes a critical issue with an SSL model's subpar performance. We aim to address the issue of labeling unlabeled data and also solve the model bias problem due to imbalanced datasets while achieving better accuracy. To accomplish this, we create "artificial" labels and train a model to have reasonable accuracy. We iteratively redistribute the classes through resampling using a distribution alignment technique. We use a variety of class imbalanced satellite image datasets: EuroSAT, UCM, and WHU-RS19. On UCM balanced dataset, our method outperforms previous methods MSMatch and FixMatch by 1.21% and 0.6%, respectively. For imbalanced EuroSAT, our method outperforms MSMatch and FixMatch by 1.08% and 1%, respectively. Our approach significantly lessens the requirement for labeled data, consistently outperforms alternative approaches, and resolves the issue of model bias caused by class imbalance in datasets.