Semi-supervised learning with constrained virtual support vector machines for classification of remote sensing image data
We introduce two semi-supervised models for the classification of remote sensing image data. The models are built upon the framework of Virtual Support Vector Machines (VSVM). Generally, VSVM follow a two-step learning procedure: A Support Vector Machines (SVM) model is learned to determine and extr...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-12-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1569843223003953 |
| _version_ | 1797389483034804224 |
|---|---|
| author | Christian Geiß Patrick Aravena Pelizari Ozan Tunçbilek Hannes Taubenböck |
| author_facet | Christian Geiß Patrick Aravena Pelizari Ozan Tunçbilek Hannes Taubenböck |
| author_sort | Christian Geiß |
| collection | DOAJ |
| description | We introduce two semi-supervised models for the classification of remote sensing image data. The models are built upon the framework of Virtual Support Vector Machines (VSVM). Generally, VSVM follow a two-step learning procedure: A Support Vector Machines (SVM) model is learned to determine and extract labeled samples that constitute the decision boundary with the maximum margin between thematic classes, i.e., the Support Vectors (SVs). The SVs govern the creation of so-called virtual samples. This is done by modifying, i.e., perturbing, the image features to which a decision boundary needs to be invariant. Subsequently, the classification model is learned for a second time by using the newly created virtual samples in addition to the SVs to eventually find a new optimal decision boundary. Here, we extend this concept by (i) integrating a constrained set of semi-labeled samples when establishing the final model. Thereby, the model constrainment, i.e., the selection mechanism for including solely informative semi-labeled samples, is built upon a self-learning procedure composed of two active learning heuristics. Additionally, (ii) we consecutively deploy semi-labeled samples for the creation of semi-labeled virtual samples by modifying the image features of semi-labeled samples that have become semi-labeled SVs after an initial model run. We present experimental results from classifying two multispectral data sets with a sub-meter geometric resolution. The proposed semi-supervised VSVM models exhibit the most favorable performance compared to related SVM and VSVM-based approaches, as well as (semi-)supervised CNNs, in situations with a very limited amount of available prior knowledge, i.e., labeled samples. |
| first_indexed | 2024-03-08T22:57:40Z |
| format | Article |
| id | doaj.art-8c9e7a594a974079856ab3284feb3168 |
| institution | Directory Open Access Journal |
| issn | 1569-8432 |
| language | English |
| last_indexed | 2024-03-08T22:57:40Z |
| publishDate | 2023-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj.art-8c9e7a594a974079856ab3284feb31682023-12-16T06:06:31ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322023-12-01125103571Semi-supervised learning with constrained virtual support vector machines for classification of remote sensing image dataChristian Geiß0Patrick Aravena Pelizari1Ozan Tunçbilek2Hannes Taubenböck3German Aerospace Center (DLR), German Remote Sensing Data Center (DFD), Münchener Straße 20, 82234 Weßling, Germany; University of Bonn, Department of Geography, Meckenheimer Allee 166, 53115 Bonn, Germany; Corresponding author at: German Aerospace Center (DLR), German Remote Sensing Data Center (DFD), Münchner Straße 20, 82234 Weßling, Germany.German Aerospace Center (DLR), German Remote Sensing Data Center (DFD), Münchener Straße 20, 82234 Weßling, Germany; University of Würzburg, Institute of Geography and Geology, Chair of Remote Sensing, Oswald-Kuelpe-Weg 86, 97074 Würzburg, GermanyGerman Aerospace Center (DLR), German Remote Sensing Data Center (DFD), Münchener Straße 20, 82234 Weßling, GermanyGerman Aerospace Center (DLR), German Remote Sensing Data Center (DFD), Münchener Straße 20, 82234 Weßling, Germany; University of Würzburg, Institute of Geography and Geology, Chair of Remote Sensing, Oswald-Kuelpe-Weg 86, 97074 Würzburg, GermanyWe introduce two semi-supervised models for the classification of remote sensing image data. The models are built upon the framework of Virtual Support Vector Machines (VSVM). Generally, VSVM follow a two-step learning procedure: A Support Vector Machines (SVM) model is learned to determine and extract labeled samples that constitute the decision boundary with the maximum margin between thematic classes, i.e., the Support Vectors (SVs). The SVs govern the creation of so-called virtual samples. This is done by modifying, i.e., perturbing, the image features to which a decision boundary needs to be invariant. Subsequently, the classification model is learned for a second time by using the newly created virtual samples in addition to the SVs to eventually find a new optimal decision boundary. Here, we extend this concept by (i) integrating a constrained set of semi-labeled samples when establishing the final model. Thereby, the model constrainment, i.e., the selection mechanism for including solely informative semi-labeled samples, is built upon a self-learning procedure composed of two active learning heuristics. Additionally, (ii) we consecutively deploy semi-labeled samples for the creation of semi-labeled virtual samples by modifying the image features of semi-labeled samples that have become semi-labeled SVs after an initial model run. We present experimental results from classifying two multispectral data sets with a sub-meter geometric resolution. The proposed semi-supervised VSVM models exhibit the most favorable performance compared to related SVM and VSVM-based approaches, as well as (semi-)supervised CNNs, in situations with a very limited amount of available prior knowledge, i.e., labeled samples.http://www.sciencedirect.com/science/article/pii/S1569843223003953Image classificationVirtual support vector machinesSemi-supervised modelsSelf-learningActive learning model heuristics |
| spellingShingle | Christian Geiß Patrick Aravena Pelizari Ozan Tunçbilek Hannes Taubenböck Semi-supervised learning with constrained virtual support vector machines for classification of remote sensing image data International Journal of Applied Earth Observations and Geoinformation Image classification Virtual support vector machines Semi-supervised models Self-learning Active learning model heuristics |
| title | Semi-supervised learning with constrained virtual support vector machines for classification of remote sensing image data |
| title_full | Semi-supervised learning with constrained virtual support vector machines for classification of remote sensing image data |
| title_fullStr | Semi-supervised learning with constrained virtual support vector machines for classification of remote sensing image data |
| title_full_unstemmed | Semi-supervised learning with constrained virtual support vector machines for classification of remote sensing image data |
| title_short | Semi-supervised learning with constrained virtual support vector machines for classification of remote sensing image data |
| title_sort | semi supervised learning with constrained virtual support vector machines for classification of remote sensing image data |
| topic | Image classification Virtual support vector machines Semi-supervised models Self-learning Active learning model heuristics |
| url | http://www.sciencedirect.com/science/article/pii/S1569843223003953 |
| work_keys_str_mv | AT christiangeiß semisupervisedlearningwithconstrainedvirtualsupportvectormachinesforclassificationofremotesensingimagedata AT patrickaravenapelizari semisupervisedlearningwithconstrainedvirtualsupportvectormachinesforclassificationofremotesensingimagedata AT ozantuncbilek semisupervisedlearningwithconstrainedvirtualsupportvectormachinesforclassificationofremotesensingimagedata AT hannestaubenbock semisupervisedlearningwithconstrainedvirtualsupportvectormachinesforclassificationofremotesensingimagedata |