Domain Adaptation for Convolutional Neural Networks Based Remote Sensing Scene Classification

Song, Shaoyue; Yu, Hongkai; Miao, Zhenjiang; Zhang, Qiang; Lin, Yuewei; Wang, Song

doi:10.1109/LGRS.2019.2896411

Title: Domain Adaptation for Convolutional Neural Networks Based Remote Sensing Scene Classification

Full Record
Other Related Research

Abstract

Remote sensing (RS) scene classification plays an important role in the field of earth observation. With the rapid development of the remote sensing techniques, a large number of RS scene images are available. Since manually labeling largescale RS scene images is both labor and time consuming, when a new unlabeled dataset is obtained, how to use the existing labeled datasets to classify the new unlabeled images is an important research direction. Different RS scene image datasets may be taken from different type of sensors, and the images may vary from imaging modalities, spatial resolutions and image scales, so the distribution discrepancy exists among different image datasets. As a result, simply applying Convolutional Neural Networks (CNN) trained on source domain cannot accurately classify the images on target domain. Domain Adaptation (DA) can be helpful to solve this problem. In this paper, we design a Subspace Alignment (SA) and CNN based framework to solve the DA problem in RS scene image classification. A new SA layer is proposed and added into CNN models for DA, which could align the source and target domains in some feature subspace. Finetuning the modified CNN model with the added SA layer is able to make themore »« less

Authors:

Song, Shaoyue ^[1]; Yu, Hongkai ^[2]; Miao, Zhenjiang ^[1]; Zhang, Qiang ^[1]; Lin, Yuewei ^[3]; Wang, Song ^[4]

Beijing Jiaotong Univ., Beijing (China)
Univ. of Texas, Edinburg, TX (United States)
Brookhaven National Lab. (BNL), Upton, NY (United States)
Univ. of South Carolina, Columbia, SC (United States); Tianjin Univ. (China)

Publication Date:: Mon Feb 25 00:00:00 EST 2019

Research Org.:: Brookhaven National Lab. (BNL), Upton, NY (United States)

Sponsoring Org.:: USDOE Office of Science (SC), Advanced Scientific Computing Research (SC-21)

OSTI Identifier:: 1492766

Report Number(s):: BNL-210923-2019-JAAM
Journal ID: ISSN 1545-598X

Grant/Contract Number:: SC0012704

Resource Type:: Accepted Manuscript

Journal Name:: IEEE Geoscience and Remote Sensing Letters

Additional Journal Information:: Journal Volume: 16; Journal Issue: 8; Journal ID: ISSN 1545-598X

Publisher:: IEEE

Country of Publication:: United States

Language:: English

Subject:: 97 MATHEMATICS AND COMPUTING

Citation Formats


                    Song, Shaoyue, Yu, Hongkai, Miao, Zhenjiang, Zhang, Qiang, Lin, Yuewei, and Wang, Song. Domain Adaptation for Convolutional Neural Networks Based Remote Sensing Scene Classification.  United States: N. p., 2019. 
Web.  doi:10.1109/LGRS.2019.2896411.

Copy to clipboard


                    Song, Shaoyue, Yu, Hongkai, Miao, Zhenjiang, Zhang, Qiang, Lin, Yuewei, & Wang, Song. Domain Adaptation for Convolutional Neural Networks Based Remote Sensing Scene Classification.  United States.  https://doi.org/10.1109/LGRS.2019.2896411

Copy to clipboard


                    Song, Shaoyue, Yu, Hongkai, Miao, Zhenjiang, Zhang, Qiang, Lin, Yuewei, and Wang, Song. Mon .  
"Domain Adaptation for Convolutional Neural Networks Based Remote Sensing Scene Classification".  United States.  https://doi.org/10.1109/LGRS.2019.2896411.  https://www.osti.gov/servlets/purl/1492766.

Copy to clipboard


                    
@article{osti_1492766,

  title        = {Domain Adaptation for Convolutional Neural Networks Based Remote Sensing Scene Classification},

  author       = {Song, Shaoyue and Yu, Hongkai and Miao, Zhenjiang and Zhang, Qiang and Lin, Yuewei and Wang, Song},

  abstractNote = {Remote sensing (RS) scene classification plays an important role in the field of earth observation. With the rapid development of the remote sensing techniques, a large number of RS scene images are available. Since manually labeling largescale RS scene images is both labor and time consuming, when a new unlabeled dataset is obtained, how to use the existing labeled datasets to classify the new unlabeled images is an important research direction. Different RS scene image datasets may be taken from different type of sensors, and the images may vary from imaging modalities, spatial resolutions and image scales, so the distribution discrepancy exists among different image datasets. As a result, simply applying Convolutional Neural Networks (CNN) trained on source domain cannot accurately classify the images on target domain. Domain Adaptation (DA) can be helpful to solve this problem. In this paper, we design a Subspace Alignment (SA) and CNN based framework to solve the DA problem in RS scene image classification. A new SA layer is proposed and added into CNN models for DA, which could align the source and target domains in some feature subspace. Finetuning the modified CNN model with the added SA layer is able to make the CNN model adapt to the aligned feature subspace and helps to relieve the domain distribution discrepancy. The experiments conducted on two public datasets show that adding the SA layer into CNN can improve the scene classification on target domain.},

  doi          = {10.1109/LGRS.2019.2896411},

  journal      = {IEEE Geoscience and Remote Sensing Letters},

  number       = 8,

  volume       = 16,

  place        = {United States},

  year         = {Mon Feb 25 00:00:00 EST 2019},

  month        = {Mon Feb 25 00:00:00 EST 2019}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Accepted Manuscript (DOE)

Publisher's Version of Record

https://doi.org/10.1109/LGRS.2019.2896411

Other availability

Search WorldCat to find libraries that may hold this journal

Citation Metrics:

Cited by: 55 works

Citation information provided by
Web of Science

Save / Share:

Export Metadata

Save to My Library

Similar Records in DOE PAGES and OSTI.GOV collections:

Convolutional Neural Networks Based Remote Sensing Scene Classification under Clear and Cloudy Environments

Conference Yu, Hongkai ; Lin, Yuewei ; Sun, H ; ...

Remote sensing (RS) scene classification has wide applications in the environmental monitoring and geological survey. In the real-world applications, the RS scene images taken by the satellite might have two scenarios: clear and cloudy environments. However, most of existing methods did not consider these two environments simultaneously. In this paper, we assume that the global and local features are iscriminative in either clear or cloudy environments. Many existing Convolution Neural Networks (CNN) based models have made excellent achievements in the image classification, however they somewhat ignored the global and local features in their network structure. In this paper, we proposemore »« less
Full Text Available
Iterative self-organizing SCEne-LEvel sampling (ISOSCELES) for large-scale building extraction

Journal Article Laverdiere, Melanie ; Yang, H. Lexie ; Rose, Amy ; ... - GIScience & Remote Sensing

Convolutional neural networks (CNN) provide state-of-the-art performance in many computer vision tasks, including those related to remote-sensing image analysis. Successfully training a CNN to generalize well to unseen data, however, requires training on samples that represent the full distribution of variation of both the target classes and their surrounding contexts. With remote sensing data, acquiring a sufficiently representative training set is a challenge due to both the inherent multi-modal variability of satellite or aerial imagery and the general high cost of labeling data. To address this challenge, we have developed ISOSCELES, an Iterative Self-Organizing SCEne LEvel Sampling method for hierarchicalmore »« less
https://doi.org/10.1080/15481603.2021.2006433

Full Text Available
Cross-Domain Recognition by Identifying Joint Subspaces of Source Domain and Target Domain

Journal Article Lin, Yuewei ; Chen, Jing ; Cao, Yu ; ... - IEEE Transactions on Cybernetics

This paper introduces here a new method to solve the cross-domain recognition problem. Different from the traditional domain adaption methods which rely on a global domain shift for all classes between the source and target domains, the proposed method is more flexible to capture individual class variations across domains. By adopting a natural and widely used assumption that the data samples from the same class should lay on an intrinsic low-dimensional subspace, even if they come from different domains, the proposed method circumvents the limitation of the global domain shift, and solves the cross-domain recognition by finding the joint subspacesmore »« less
Cited by 21
https://doi.org/10.1109/TCYB.2016.2538199

Full Text Available
DeepAstroUDA: semi-supervised universal domain adaptation for cross-survey galaxy morphology classification and anomaly detection

Journal Article Ćiprijanović, A. ; Lewis, A. ; Pedro, K. ; ... - Machine Learning: Science and Technology

Artificial intelligence methods show great promise in increasing the quality and speed of work with large astronomical datasets, but the high complexity of these methods leads to the extraction of dataset-specific, non-robust features. Therefore, such methods do not generalize well across multiple datasets. We present a universal domain adaptation method, DeepAstroUDA, as an approach to overcome this challenge. This algorithm performs semi-supervised domain adaptation (DA) and can be applied to datasets with different data distributions and class overlaps. Non-overlapping classes can be present in any of the two datasets (the labeled source domain, or the unlabeled target domain), and themore »« less
https://doi.org/10.1088/2632-2153/acca5f
Self-Supervised Cloud Classification

Journal Article Geiss, Andrew ; Christensen, Matthew W. ; Varble, Adam C. ; ... - Artificial Intelligence for the Earth Systems

Low-level marine clouds play a pivotal role in Earth’s weather and climate through their interactions with radiation, heat and moisture transport, and the hydrological cycle. These interactions depend on a range of dynamical and microphysical processes that result in a broad diversity of cloud types and spatial structures, and a comprehensive understanding of cloud morphology is critical for continued improvement of our atmospheric modeling and prediction capabilities moving forward. Deep learning has recently accelerated our ability to study clouds using satellite remote sensing, and machine learning classifiers have enabled detailed studies of cloud morphology. A major limitation of deep learningmore »« less
https://doi.org/10.1175/AIES-D-23-0036.1

Similar Records