GFCNet: Contrastive Learning Network with Geography Feature Space Joint Negative Sample Correction for Land Cover Classification
Open Access
- 21 October 2023
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 15 (20) , 5056
Abstract
With the continuous improvement in the volume and spatial resolution of remote sensing images, the self-supervised contrastive learning paradigm driven by a large amount of unlabeled data is expected to be a promising solution for large-scale land cover classification with limited labeled data. However, due to the richness and scale diversity of ground objects contained in remote sensing images, self-supervised contrastive learning encounters two challenges when performing large-scale land cover classification: (1) Self-supervised contrastive learning models treat random spatial–spectral transformations of different images as negative samples, even though they may contain the same ground objects, which leads to serious class confusion in land cover classification. (2) The existing self-supervised contrastive learning models simply use the single-scale features extracted by the feature extractor for land cover classification, which limits the ability of the model to capture different scales of ground objects in remote sensing images. In this study, we propose a contrastive learning network with Geography Feature space joint negative sample Correction (GFCNet) for land cover classification. To address class confusion, we propose a Geography Feature space joint negative sample Correction Strategy (GFCS), which integrates the geography space and feature space relationships of different images to construct negative samples, reducing the risk of negative samples containing the same ground object. In order to improve the ability of the model to capture the features of different scale ground objects, we adopt a Multi-scale Feature joint Fine-tuning Strategy (MFFS) to integrate different scale features obtained by the self-supervised contrastive learning network for land cover classification tasks. We evaluate the proposed GFCNet on three public land cover classification datasets and achieve the best results compared to seven baselines of self-supervised contrastive learning methods. Specifically, on the LoveDA Rural dataset, the proposed GFCNet improves 3.87% in Kappa and 1.54% in mIoU compared with the best baseline.Keywords
Funding Information
- Major Program Project of Xiangjiang Laboratory (22XJ01010)
This publication has 50 references indexed in Scilit:
- A Two-Branch CNN Architecture for Land Cover Classification of PAN and MS ImageryRemote Sensing, 2018
- Deep Clustering for Unsupervised Learning of Visual Features2018
- Introducing Eurosat: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification2018
- Implementation of machine-learning classification in remote sensing: an applied reviewInternational Journal of Remote Sensing, 2018
- Developments in Landsat Land Cover Classification Methods: A ReviewRemote Sensing, 2017
- Deep Learning Classification of Land Cover and Crop Types Using Remote Sensing DataIEEE Geoscience and Remote Sensing Letters, 2017
- Deep Learning for Remote Sensing Data: A Technical Tutorial on the State of the ArtIEEE Geoscience and Remote Sensing Magazine, 2016
- Land-use/cover classification in a heterogeneous coastal landscape using RapidEye imagery: evaluating the performance of random forest and support vector machines classifiersInternational Journal of Remote Sensing, 2014
- An assessment of support vector machines for land cover classificationInternational Journal of Remote Sensing, 2002
- Land cover mapping of large areas from satellites: Status and research prioritiesInternational Journal of Remote Sensing, 2000