paper-with-me

홈 › Papers

A Self-Supervised Approach to Land Cover Segmentation

2023-10-27 · Charles Moore, Dakota Hester

Land use/land cover change (LULC) maps are integral resources in earth science and agricultural research. Due to the nature of such maps, the creation of LULC maps is often constrained by the time and human resources necessary to accurately annotate satellite imagery and remote sensing data. While computer vision models that perform semantic segmentation to create detailed labels from such data are not uncommon, litle research has been done on self-supervised and unsupervised approaches to labelling LULC maps without the use of ground-truth masks. Here, we demonstrate a self-supervised method of land cover segmentation that has no need for high-quality ground truth labels. The proposed deep learning employs a frozen pre-trained ViT backbone transferred from DINO in a STEGO architecture and is fine-tuned using a custom dataset consisting of very high resolution (VHR) sattelite imagery. After only 10 epochs of fine-tuning, an accuracy of roughly 52% was observed across 5 samples, signifying the feasibility of self-supervised models for the automated labelling of VHR LULC maps.

📄 PDF Abstract BibTeX arXiv:2310.18251

Code (0)

등록된 구현이 없습니다.

Tasks

Semantic Segmentation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Multi-Head Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…

Similar Papers 제목 키워드 기반

Supervised and self-supervised land-cover segmentation & classification of the Biesbosch wetlands

2025-05-27 · Eva Gmelich Meijling, Roberto Del Prete, Arnoud Visser

Accurate wetland land-cover classification is essential for environmental monitoring, biodiversity assessment, and sustainable ecosystem management. However, the scarcity of annotated data, especially for high-resolution…

Land Cover ClassificationSelf-Supervised Learning

Learning with less: label-efficient land cover classification at very high spatial resolution using self-supervised deep learning

2025-11-04 · Dakota Hester, Vitor S. Martins, Lucas B. Ferreira, Thainara M. A. Lima arxiv

Deep learning semantic segmentation methods have shown promising performance for very high 1-m resolution land cover classification, but the challenge of collecting large volumes of representative training data creates a…

Self-Supervised LearningSemantic Segmentation

Embedding Earth: Self-supervised contrastive pre-training for dense land cover classification

2022-03-11 · Michail Tarasiou, Stefanos Zafeiriou

In training machine learning models for land cover semantic segmentation there is a stark contrast between the availability of satellite imagery to be used as inputs and ground truth data to enable supervised learning. W…

Earth ObservationLand Cover ClassificationSemantic Segmentation

Ben-ge: Extending BigEarthNet with Geographical and Environmental Data

2023-07-04 · Michael Mommert, Nicolas Kesseli, Joëlle Hanna, Linus Scheibenreif 외

Deep learning methods have proven to be a powerful tool in the analysis of large amounts of complex Earth observation data. However, while Earth observation data are multi-modal in most cases, only single or few modaliti…

Earth ObservationLand Cover Classification

SeasoNet: A Seasonal Scene Classification, segmentation and Retrieval dataset for satellite Imagery over Germany

2022-07-19 · Dominik Koßmann, Viktor Brack, Thorsten Wilhelm

This work presents SeasoNet, a new large-scale multi-label land cover and land use scene understanding dataset. It includes $1\,759\,830$ images from Sentinel-2 tiles, with 12 spectral bands and patch sizes of up to $ 12…

Image RetrievalRetrievalScene ClassificationScene Understanding+1