• Home
  • Search
  • A Bayesian-inspired, deep learning-based, semi-supervised domain adaptation technique for land cover mapping
  • Cite Icon35
  • https://doi.org/10.1007/s10994-020-05942-zCopy DOI Icon

A Bayesian-inspired, deep learning-based, semi-supervised domain adaptation technique for land cover mapping

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Land cover maps are a vital input variable to many types of environmental research and management. While they can be produced automatically by machine learning techniques, these techniques require substantial training data to achieve high levels of accuracy, which are not always available. One technique researchers use when labelled training data are scarce is domain adaptation (DA)—where data from an alternate region, known as the source domain, are used to train a classifier and this model is adapted to map the study region, or target domain. The scenario we address in this paper is known as semi-supervised DA, where some labelled samples are available in the target domain. In this paper we present Sourcerer, a Bayesian-inspired, deep learning-based, semi-supervised DA technique for producing land cover maps from satellite image time series (SITS) data. The technique takes a convolutional neural network trained on a source domain and then trains further on the available target domain with a novel regularizer applied to the model weights. The regularizer adjusts the degree to which the model is modified to fit the target data, limiting the degree of change when the target data are few in number and increasing it as target data quantity increases. Our experiments on Sentinel-2 time series images compare Sourcerer with two state-of-the-art semi-supervised domain adaptation techniques and four baseline models. We show that on two different source-target domain pairings Sourcerer outperforms all other methods for any quantity of labelled target data available. In fact, the results on the more difficult target domain show that the starting accuracy of Sourcerer (when no labelled target data are available), 74.2%, is greater than the next-best state-of-the-art method trained on 20,000 labelled target instances.

Similar Papers
  • Conference Article
  • Citations4

Exploring Data Quantity Requirements for Domain Adaptation in the Classification of Satellite Image Time Series

  • Aug 01, 2019
  • Benjamin Lucas +5
  • Conference Article
  • Citations8

Learning Target Predictive Function without Target Labels

  • Dec 01, 2012
  • Chun-Wei Seah +3
  • Research Article
  • Citations2

Multi-source semi-supervised condition constrained domain adaptation for process fault classification

  • Feb 28, 2025
  • Engineering Research Express
  • Xiaoping Guo +2
  • Research Article
  • Citations57

A Novel Domain Adaptation Bayesian Classifier for Updating Land-Cover Maps With Class Differences in Source and Target Domains

  • Jul 01, 2012
  • IEEE Transactions on Geoscience and Remote Sensing
  • Kanchan Bahirat +3
  • Research Article
  • Citations7

Improving cross-regional model transfer performance in crop classification by crop time series correction

  • Oct 21, 2024
  • Geo-spatial Information Science
  • Hengbin Wang +8
  • Conference Article
  • Citations13

Unsupervised Domain Adaptation Techniques for Classification of Satellite Image Time Series

  • Sep 26, 2020
  • Benjamin Lucas +4
  • Research Article
  • Citations37

Unsupervised Adversarial Domain Adaptation Network for Semantic Segmentation

  • Dec 26, 2019
  • IEEE Geoscience and Remote Sensing Letters
  • Wei Liu +1
  • Conference Article
  • Citations4

Domain-Adaptive TinyML Model for Efficient Pest and Disease Detection in Domestic Crops: A Practical Approach for Developing Countries

  • Sep 04, 2024
  • Gibson Kimutai +1
  • Conference Article
  • Citations4

Machine Learning Pipeline for Reusing Pretrained Models

  • Nov 02, 2020
  • Maryam Alshehhi +1
  • Conference Article
  • Citations137

Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation

  • Jun 01, 2021
  • Jichang Li +3
  • PDF
  • Research Article
  • Citations14

ADVERSARIAL DOMAIN ADAPTATION FOR THE CLASSIFICATION OF AERIAL IMAGES AND HEIGHT DATA USING CONVOLUTIONAL NEURAL NETWORKS

  • Sep 16, 2019
  • ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
  • D Wittich +1
  • PDF
  • Research Article
  • Citations2

Multi-Source Domain Adaptation Using Ambient Sensor Data

  • Nov 19, 2024
  • Applied Artificial Intelligence
  • Jawher Dridi +2
  • Conference Article
  • Citations5

Deep Domain Adaptation based Cloud Type Detection using Active and Passive Satellite Data

  • Dec 10, 2020
  • Xin Huang +6
  • Conference Article
  • Citations2

Unsupervised Domain Adaptation Methods for Land Cover Mapping with Optical Satellite Image Time Series

  • Jul 17, 2022
  • E Capliez +4
  • PDF
  • Research Article
  • Citations3

NuSegDA: Domain adaptation for nuclei segmentation

  • Mar 02, 2023
  • Frontiers in Big Data
  • Mohammad Minhazul Haq +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.