GeoBoost: An Incremental Deep Learning Approach toward Global Mapping of Buildings from VHR Remote Sensing Images

GeoBoost: An Incremental Deep Learning Approach toward Global Mapping of Buildings from VHR Remote Sensing Images

Modern convolutional neural networks (CNNs) are often trained on pre-set data sets with a fixed size. As for the large-scale applications of satellite images, for example, global or regional mappings, these images are collected incrementally by multiple stages in general. In other words, the sizes o...

Full description

Bibliographic Details
Main Authors: Naisen Yang, Hong Tang
Format: Article
Language:English
Published: MDPI AG 2020-06-01
Series:Remote Sensing
Subjects:
building extraction
data-incremental learning
GeoBoost
convolutional neural networks
semantic segmentation
Online Access:https://www.mdpi.com/2072-4292/12/11/1794
id doaj-96034c388a3147f088178e887badd04b
record_format Article
spelling doaj-96034c388a3147f088178e887badd04b2020-11-25T03:10:52ZengMDPI AGRemote Sensing2072-42922020-06-01121794179410.3390/rs12111794GeoBoost: An Incremental Deep Learning Approach toward Global Mapping of Buildings from VHR Remote Sensing ImagesNaisen Yang0Hong Tang1State Key Laboratory of Remote Sensing Science, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaState Key Laboratory of Remote Sensing Science, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaModern convolutional neural networks (CNNs) are often trained on pre-set data sets with a fixed size. As for the large-scale applications of satellite images, for example, global or regional mappings, these images are collected incrementally by multiple stages in general. In other words, the sizes of training datasets might be increased for the tasks of mapping rather than be fixed beforehand. In this paper, we present a novel algorithm, called GeoBoost, for the incremental-learning tasks of semantic segmentation via convolutional neural networks. Specifically, the GeoBoost algorithm is trained in an end-to-end manner on the newly available data, and it does not decrease the performance of previously trained models. The effectiveness of the GeoBoost algorithm is verified on the large-scale data set of DREAM-B. This method avoids the need for training on the enlarged data set from scratch and would become more effective along with more available data.https://www.mdpi.com/2072-4292/12/11/1794building extractiondata-incremental learningGeoBoostconvolutional neural networkssemantic segmentation
collection DOAJ
language English
format Article
sources DOAJ
author Naisen Yang
Hong Tang
spellingShingle Naisen Yang
Hong Tang
GeoBoost: An Incremental Deep Learning Approach toward Global Mapping of Buildings from VHR Remote Sensing Images
Remote Sensing
building extraction
data-incremental learning
GeoBoost
convolutional neural networks
semantic segmentation
author_facet Naisen Yang
Hong Tang
author_sort Naisen Yang
title GeoBoost: An Incremental Deep Learning Approach toward Global Mapping of Buildings from VHR Remote Sensing Images
title_short GeoBoost: An Incremental Deep Learning Approach toward Global Mapping of Buildings from VHR Remote Sensing Images
title_full GeoBoost: An Incremental Deep Learning Approach toward Global Mapping of Buildings from VHR Remote Sensing Images
title_fullStr GeoBoost: An Incremental Deep Learning Approach toward Global Mapping of Buildings from VHR Remote Sensing Images
title_full_unstemmed GeoBoost: An Incremental Deep Learning Approach toward Global Mapping of Buildings from VHR Remote Sensing Images
title_sort geoboost: an incremental deep learning approach toward global mapping of buildings from vhr remote sensing images
publisher MDPI AG
series Remote Sensing
issn 2072-4292
publishDate 2020-06-01
description Modern convolutional neural networks (CNNs) are often trained on pre-set data sets with a fixed size. As for the large-scale applications of satellite images, for example, global or regional mappings, these images are collected incrementally by multiple stages in general. In other words, the sizes of training datasets might be increased for the tasks of mapping rather than be fixed beforehand. In this paper, we present a novel algorithm, called GeoBoost, for the incremental-learning tasks of semantic segmentation via convolutional neural networks. Specifically, the GeoBoost algorithm is trained in an end-to-end manner on the newly available data, and it does not decrease the performance of previously trained models. The effectiveness of the GeoBoost algorithm is verified on the large-scale data set of DREAM-B. This method avoids the need for training on the enlarged data set from scratch and would become more effective along with more available data.
topic building extraction
data-incremental learning
GeoBoost
convolutional neural networks
semantic segmentation
url https://www.mdpi.com/2072-4292/12/11/1794
work_keys_str_mv AT naisenyang geoboostanincrementaldeeplearningapproachtowardglobalmappingofbuildingsfromvhrremotesensingimages
AT hongtang geoboostanincrementaldeeplearningapproachtowardglobalmappingofbuildingsfromvhrremotesensingimages
_version_ 1724656819611107328

Similar Items