SELF-TRAINING FOR SEMI-SUPERVISED DEEP CONTOUR DETECTION OF SURFACE WATER
Abstract. Contour detection is better for monitoring dynamic and long-term changes to surface water bodies. For that purpose, we present a semi-automated method for collecting and labeling water contours from Landsat-8 and Sentinel-2 images. Due to the need for human inspection, the method has thus far generated 14K labeled images from more than 1.5M images. Given the cost of data labeling, we propose a deep semi-supervised self-learning system performed in two training stages, known as teacher-student. The teacher is trained on the accurate human-labeled data, then used to pseudo label the remaining unlabeled data. The student is trained on both human-labeled and machine pseudo-labeled data. For both teacher and student, we use a uniquely designed multiscale UNet classifier that uses fewer parameters and is more accurate than other state-of-the-art classifiers. Random augmentations are used to “noise” the student model and improve its generalization, and normalization schemes are used to blend the human-labeled loss with the machine-labeled loss. Comparisons to existing water body detection classifiers and segmentation classifiers show the superiority of our proposed system in detecting water contours.
- Location
-
Deutsche Nationalbibliothek Frankfurt am Main
- Extent
-
Online-Ressource
- Language
-
Englisch
- Bibliographic citation
-
SELF-TRAINING FOR SEMI-SUPERVISED DEEP CONTOUR DETECTION OF SURFACE WATER ; volume:XLIII-B3-2022 ; year:2022 ; pages:1393-1398 ; extent:6
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ; XLIII-B3-2022 (2022), 1393-1398 (gesamt 6)
- Creator
-
Alsamman, A.
Syed, M. B.
- DOI
-
10.5194/isprs-archives-XLIII-B3-2022-1393-2022
- URN
-
urn:nbn:de:101:1-2022060205240631978221
- Rights
-
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
- Last update
-
15.08.2025, 7:35 AM CEST
Data provider
Deutsche Nationalbibliothek. If you have any questions about the object, please contact the data provider.
Associated
- Alsamman, A.
- Syed, M. B.
Other Objects (12)
Semi-supervised data cleaning
Deep semi-supervised learning for brain tumor classification
Semi-supervised structured prediction models
Semi-supervised protein subcellular localization
Comparison of semi-supervised deep learning algorithms for audio classification
A survey on semi-supervised learning
Semi-supervised learning for image classification
Semi-supervised discovery of differential genes
Semi-supervised classifier guided by discriminator
Feature ranking for semi-supervised learning
Deep echocardiography: data-efficient supervised and semi-supervised deep learning towards automated diagnosis of cardiac disease
Semi-supervised contour-driven broad learning system for autonomous segmentation of concealed prohibited baggage items
Semi-supervised data cleaning
Deep semi-supervised learning for brain tumor classification
Semi-supervised structured prediction models
Semi-supervised protein subcellular localization
Comparison of semi-supervised deep learning algorithms for audio classification
A survey on semi-supervised learning
Semi-supervised learning for image classification
Semi-supervised discovery of differential genes
Semi-supervised classifier guided by discriminator
Feature ranking for semi-supervised learning
Deep echocardiography: data-efficient supervised and semi-supervised deep learning towards automated diagnosis of cardiac disease
Semi-supervised contour-driven broad learning system for autonomous segmentation of concealed prohibited baggage items
Semi-supervised data cleaning
Deep semi-supervised learning for brain tumor classification
Semi-supervised structured prediction models
Semi-supervised protein subcellular localization
Comparison of semi-supervised deep learning algorithms for audio classification
A survey on semi-supervised learning
Semi-supervised learning for image classification
Semi-supervised discovery of differential genes
Semi-supervised classifier guided by discriminator
Feature ranking for semi-supervised learning
Deep echocardiography: data-efficient supervised and semi-supervised deep learning towards automated diagnosis of cardiac disease