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

Autor: Jihwan P. Choi, Younghwan Na, Jae Youn Hwang, Kyungsu Lee, Juhum Park, Jun Hee Kim
Rok vydání: 2021
Předmět:
FOS: Computer and information sciences
Computer Science - Machine Learning
Computer science
Computer Vision and Pattern Recognition (cs.CV)
Feature extraction
Computer Science - Computer Vision and Pattern Recognition
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
0211 other engineering and technologies
Machine Learning (stat.ML)
02 engineering and technology
Machine Learning (cs.LG)
Data modeling
Statistics - Machine Learning
FOS: Electrical engineering
electronic engineering
information engineering
Segmentation
Electrical and Electronic Engineering
Aerial image
021101 geological & geomatics engineering
business.industry
Intersection (set theory)
Image and Video Processing (eess.IV)
Pattern recognition
Image segmentation
Electrical Engineering and Systems Science - Image and Video Processing
Data set
General Earth and Planetary Sciences
Artificial intelligence
business
Test data
Zdroj: IEEE Transactions on Geoscience and Remote Sensing. 59:5171-5182
ISSN: 1558-0644
0196-2892
DOI: 10.1109/tgrs.2020.3010055
Popis: 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 datasets, CNN-based segmentation models trained by a training dataset fail to segment buildings for the test dataset. In this paper, 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 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-dataset experiments and the ablation study are conducted for the three different datasets: the Inria aerial image labeling dataset, the Massachusetts building dataset, and the WHU East Asia dataset. Compared to the performance of the segmentation network without the DATA scheme, the proposed method shows improvements in the overall IoU. Moreover, it is verified that the proposed method outperforms even when compared to feature adaptation (FA) and output space adaptation (OSA).
11pages, 12 figures
Databáze: OpenAIRE
Externí odkaz: