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

@article{Lucas2020ABD,
  title={A Bayesian-inspired, deep learning, semi-supervised domain adaptation technique for land cover mapping},
  author={Benjamin Lucas and Charlotte Pelletier and Daniel F. Schmidt and Geoffrey I. Webb and Franccois Petitjean},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.11930}
}
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… Expand
1 Citations
A Survey on Semi-parametric Machine Learning Technique for Time Series Forecasting
TLDR
A primer survey on the GML framework, a comprehensive overview of the existing semi-parametric machine learning techniques for time series forecasting, is provided for researchers. Expand

References

SHOWING 1-10 OF 82 REFERENCES
Exploring Data Quantity Requirements for Domain Adaptation in the Classification of Satellite Image Time Series
TLDR
This paper looks at the result of training a convolutional neural network model on a region where data are available (source domain), and then adapting this model to another region (target domain) by retraining it on the available labelled data, and in particular how these results change with increasing data availability. Expand
Active Learning for Domain Adaptation in the Supervised Classification of Remote Sensing Images
TLDR
A novel technique for addressing domain adaptation (DA) problems with active learning (AL) in the classification of remote sensing images is presented and a convergence criterion is defined that allows the technique to stop the iterative AL process on the target domain without relying on the availability of a test set for it. Expand
Domain Adaptation for the Classification of Remote Sensing Data: An Overview of Recent Advances
TLDR
A critical review of the recent advances in DA approaches for remote sensing is provided and an overview of DA methods divided into four categories: 1) invariant feature selection, 2) representation matching, 3) adaptation of classifiers, and 4) selective sampling are presented. Expand
Updating Land-Cover Maps by Classification of Image Time Series: A Novel Change-Detection-Driven Transfer Learning Approach
TLDR
Experimental results show that transferring the class labels from the source domain to the target domain provides a reliable initial training set and that the priority rule for AL results in a fast convergence to the desired accuracy with respect to Standard AL. Expand
DeepJDOT: Deep Joint distribution optimal transport for unsupervised domain adaptation
TLDR
Through a measure of discrepancy on joint deep representations/labels based on optimal transport, this work not only learns new data representations aligned between the source and target domain, but also simultaneously preserve the discriminative information used by the classifier. Expand
Temporal Convolutional Neural Network for the Classification of Satellite Image Time Series
TLDR
Experimental results show that TempCNNs are more accurate than RF and RNNs, that are the current state of the art for SITS classification, and the visual quality of the land cover maps produced by tempCNNs is assessed. Expand
SVM-Based Boosting of Active Learning Strategies for Efficient Domain Adaptation
TLDR
Experiments on two VHR QuickBird images and on a hyperspectral AVIRIS image prove the validity of the proposed adaptive approach with respect to existing techniques not involving any adjustments to the target domain. Expand
An Entropic Optimal Transport Loss for Learning Deep Neural Networks under Label Noise in Remote Sensing Images
TLDR
This work proposes an original solution with entropic optimal transportation that allows to learn in an end-to-end fashion deep neural networks that are robust to inaccurately labeled samples and proves to be highly tolerant to significant amounts of label noise. Expand
Using active learning to adapt remote sensing image classifiers
TLDR
This paper proposes to perform adaptation by sampling new training examples in unknown areas of the image to select pixels in an intelligent fashion that minimizes their number and maximizes their information content. Expand
Domain-Adversarial Training of Neural Networks
TLDR
A new representation learning approach for domain adaptation, in which data at training and test time come from similar but different distributions, which can be achieved in almost any feed-forward model by augmenting it with few standard layers and a new gradient reversal layer. Expand
...
1
2
3
4
5
...