skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Large Scale Unsupervised Domain Adaptation of Segmentation Networks with Adversarial Learning

Abstract

Most current state-of-the-art methods for semantic segmentation on remote sensing imagery require large labeled data, which is scarcely available. Due to the distribution shifting phenomenon inherent in remote sensing imagery, the reuse of pre-trained models on new areas of interest rarely yield satisfactory results. In this paper, we approach this problem from an adversarial learning perspective toward unsupervised domain adaptation. The core concept is to infuse fully convolutional neural networks and adversarial networks for semantic segmentation assuming the structures in the scene and objects of interest are similar in two set of images. Models are trained on a source dataset where ground truth is available and adapted to new target dataset iteratively via a adversarial loss on unlabeled samples. We use two real large scale datasets to validate the framework: 1) cross city road extraction and 2) cross country building extraction. The preliminary results show the usefulness of considering adversarial learning for indirect re-use of the pre-trained models. Experimental validation suggests significant benefits over models without adaptation.

Authors:
 [1]; ORCiD logo [1];  [1]; ORCiD logo [1]
  1. ORNL
Publication Date:
Research Org.:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1606898
DOE Contract Number:  
AC05-00OR22725
Resource Type:
Conference
Resource Relation:
Conference: 2019 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2019) - Yokohama, , Japan - 7/28/2019 12:00:00 PM-8/2/2019 12:00:00 PM
Country of Publication:
United States
Language:
English

Citation Formats

Deng, Xueqing, Yang, Lexie, Makkar, Nikhil, and Lunga, Dalton D. Large Scale Unsupervised Domain Adaptation of Segmentation Networks with Adversarial Learning. United States: N. p., 2019. Web. doi:10.1109/IGARSS.2019.8900277.
Deng, Xueqing, Yang, Lexie, Makkar, Nikhil, & Lunga, Dalton D. Large Scale Unsupervised Domain Adaptation of Segmentation Networks with Adversarial Learning. United States. https://doi.org/10.1109/IGARSS.2019.8900277
Deng, Xueqing, Yang, Lexie, Makkar, Nikhil, and Lunga, Dalton D. 2019. "Large Scale Unsupervised Domain Adaptation of Segmentation Networks with Adversarial Learning". United States. https://doi.org/10.1109/IGARSS.2019.8900277. https://www.osti.gov/servlets/purl/1606898.
@article{osti_1606898,
title = {Large Scale Unsupervised Domain Adaptation of Segmentation Networks with Adversarial Learning},
author = {Deng, Xueqing and Yang, Lexie and Makkar, Nikhil and Lunga, Dalton D.},
abstractNote = {Most current state-of-the-art methods for semantic segmentation on remote sensing imagery require large labeled data, which is scarcely available. Due to the distribution shifting phenomenon inherent in remote sensing imagery, the reuse of pre-trained models on new areas of interest rarely yield satisfactory results. In this paper, we approach this problem from an adversarial learning perspective toward unsupervised domain adaptation. The core concept is to infuse fully convolutional neural networks and adversarial networks for semantic segmentation assuming the structures in the scene and objects of interest are similar in two set of images. Models are trained on a source dataset where ground truth is available and adapted to new target dataset iteratively via a adversarial loss on unlabeled samples. We use two real large scale datasets to validate the framework: 1) cross city road extraction and 2) cross country building extraction. The preliminary results show the usefulness of considering adversarial learning for indirect re-use of the pre-trained models. Experimental validation suggests significant benefits over models without adaptation.},
doi = {10.1109/IGARSS.2019.8900277},
url = {https://www.osti.gov/biblio/1606898}, journal = {},
number = ,
volume = ,
place = {United States},
year = {2019},
month = {7}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share: