Cited time in webofscience Cited time in scopus

Domain Adaptive Transfer Attack-Based Segmentation Networks for Building Extraction From Aerial Images

Title
Domain Adaptive Transfer Attack-Based Segmentation Networks for Building Extraction From Aerial Images
Author(s)
Na, YounghwanKim, Jun HeeLee, KyungsuPark, JuhumHwang, Jae YounChoi, Jihwan P.
Issued Date
2021-06
Citation
IEEE Transactions on Geoscience and Remote Sensing, v.59, no.6, pp.5171 - 5182
Type
Article
Author Keywords
Image segmentationSemanticsAdaptation modelsData modelsFeature extractionTrainingBuildingsAdversarial networkbuilding extractiondomain adaptationsemantic segmentation
Keywords
DEEPCLASSIFICATION
ISSN
0196-2892
Abstract
Semantic segmentation models based on convolutional neural networks (CNNs) have gained much attention in relation to remote sensing and have achieved remarkable performance for the extraction of buildings from high-resolution aerial images. However, the issue of limited generalization for unseen images remains. When there is a domain gap between the training and test data sets, the CNN-based segmentation models trained by a training data set fail to segment buildings for the test data set. In this article, we propose segmentation networks based on a domain adaptive transfer attack (DATA) scheme for building extraction from aerial images. The proposed system combines the domain transfer and the adversarial attack concepts. Based on the DATA scheme, the distribution of the input images can be shifted to that of the target images while turning images into adversarial examples against a target network. Defending adversarial examples adapted to the target domain can overcome the performance degradation due to the domain gap and increase the robustness of the segmentation model. Cross-data set experiments and ablation study are conducted for three different data sets: the Inria aerial image labeling data set, the Massachusetts building data set, and the WHU East Asia data set. Compared with the performance of the segmentation network without the DATA scheme, the proposed method shows improvements in the overall intersection over union (IoU). Moreover, it is verified that the proposed method outperforms even when compared with feature adaptation (FA) and output space adaptation (OSA).
URI
http://hdl.handle.net/20.500.11750/12697
DOI
10.1109/tgrs.2020.3010055
Publisher
Institute of Electrical and Electronics Engineers
Related Researcher
  • 황재윤 Hwang, Jae Youn
  • Research Interests Multimodal Imaging; High-Frequency Ultrasound Microbeam; Ultrasound Imaging and Analysis; 스마트 헬스케어; Biomedical optical system
Files in This Item:

There are no files associated with this item.

Appears in Collections:
Department of Electrical Engineering and Computer Science MBIS(Multimodal Biomedical Imaging and System) Laboratory 1. Journal Articles
Department of Electrical Engineering and Computer Science NCRG(Networks and Communications Research Group) 1. Journal Articles

qrcode

  • twitter
  • facebook
  • mendeley

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE