Aligning Discriminative and Representative Features: An Unsupervised Domain Adaptation Method for Building Damage Assessment

Li, Yundong; Hu, Wei; Li, Hongguang; Han, Dong; Zhang, Baochang; Qiu, Tian

doi:10.1109/tip.2020.2988175

Cited by 22 publications

(11 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DAN [12]: DAN is a MMD-based method in which multiple task-specific layers are used to align features. ADRF [13]: ADRF is also a MMD-based domain adaptation method, which was proposed for the building damage detection of post-hurricane images. ADDA [14]: ADDA is a GANbased method which can align features.…”

Section: Resultsmentioning

confidence: 99%

Unsupervised Building Damage Identification Using Post-Event Optical Imagery and Variational Autoencoder

Lin

Wang

2021

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

Rapid building damage identification plays a vital role in rescue operations when disasters strike, especially when rescue resources are limited. In the past years, supervised machine learning has made considerable progress in building damage identification. However, the usage of supervised machine learning remains challenging due to the following facts: 1) the massive samples from the current damage imagery are difficult to be labeled and thus cannot satisfy the training requirement of deep learning, and 2) the similarity between partially damaged and undamaged buildings is high, hindering accurate classification. Leveraging the abundant samples of auxiliary domains, domain adaptation aims to transfer a classifier trained by historical damage imagery to the current task. However, traditional domain adaptation approaches do not fully consider the category-specific information during feature adaptation, which might cause negative transfer. To address this issue, we propose a novel domain adaptation framework that individually aligns each category of the target domain to that of the source domain. Our method combines the variational autoencoder (VAE) and the Gaussian mixture model (GMM). First, the GMM is established to characterize the distribution of the source domain. Then, the VAE is constructed to extract the feature of the target domain. Finally, the Kullback-Leibler (KL) divergence is minimized to force the feature of the target domain to observe the GMM of the source domain. Two damage detection tasks using post-earthquake and post-hurricane imageries are utilized to verify the effectiveness of our method. Experiments show that the proposed method obtains improvements of 4.4% and 9.5%, respectively, compared with the conventional method.

show abstract

Section: Resultsmentioning

confidence: 99%

Unsupervised Building Damage Identification Using Post-Event Optical Imagery and Variational Autoencoder

Lin

Wang

2021

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The referred network is then used to extract bitemporal deep features. In [60], variational autoencoders were used to align the distribution of deep features from different domains, from which one domain consisted of labeled samples, whereas the other domain contained nonlabeled samples. It is our belief that such networks can be adapted to follow the DSS approach as a constraint in the calibration process (i.e., a term in the loss function).…”

Section: Discussionmentioning

confidence: 99%

Disaster Intensity-Based Selection of Training Samples for Remote Sensing Building Damage Classification

Moya

Geis

Hashimoto

et al. 2021

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Previous applications of machine learning in remote sensing for the identification of damaged buildings in the aftermath of a large-scale disaster have been successful. However, standard methods do not consider the complexity and costs of compiling a training data set after a large-scale disaster. In this article, we study disaster events in which the intensity can be modeled via numerical simulation and/or instrumentation. For such cases, two fully automatic procedures for the detection of severely damaged buildings are introduced. The fundamental assumption is that samples that are located in areas with low disaster intensity mainly represent nondamaged buildings. Furthermore, areas with moderate to strong disaster intensities likely contain damaged and nondamaged buildings. Under this assumption, a procedure that is based on the automatic selection of training samples for learning and calibrating the standard support vector machine classifier is utilized. The second procedure is based on the use of two regularization parameters to define the support vectors. These frameworks avoid the collection of labeled building samples via field surveys and/or visual inspection of optical images, which requires a significant amount of time. The performance of the proposed method is evaluated via application to three real cases: the 2011 Tohoku-Oki earthquake-tsunami, the 2016 Kumamoto earthquake, and the 2018 Okayama floods. The resulted accuracy ranges between 0.85 and 0.89, and thus, it shows that the result can be used for the rapid allocation of affected buildings.

show abstract

“…It is developed on the basis of Sparse Bayesian Learning (SBL). An application for an unsupervised learning approach was presented in [13] where the authors propose a transfer learning approach to use a source network trained on a labeled dataset to be able to train the target network on an unlabeled dataset.…”

Section: Buildings Damage Assessmentmentioning

confidence: 99%

Buildings Classification using Very High Resolution Satellite Imagery

Dimassi¹,

Samhat²,

Zaraket³

et al. 2021

Preprint

View full text Add to dashboard Cite

Buildings classification using satellite images is becoming more important for several applications such as damage assessment, resource allocation, and population estimation. We focus, in this work, on buildings damage assessment (BDA) and buildings type classification (BTC) of residential and non-residential buildings. We propose to rely solely on RGB satellite images and follow a 2-stage deep learning-based approach, where first, buildings' footprints are extracted using a semantic segmentation model, followed by classification of the cropped images. Due to the lack of an appropriate dataset for the residential/non-residential building classification, we introduce a new dataset of high-resolution satellite images. We conduct extensive experiments to select the best hyper-parameters, model architecture, and training paradigm, and we propose a new transfer learning-based approach that outperforms classical methods. Finally, we validate the proposed approach on two applications showing excellent accuracy and F1-score metrics.

show abstract

Aligning Discriminative and Representative Features: An Unsupervised Domain Adaptation Method for Building Damage Assessment

Cited by 22 publications

References 33 publications

Unsupervised Building Damage Identification Using Post-Event Optical Imagery and Variational Autoencoder

Unsupervised Building Damage Identification Using Post-Event Optical Imagery and Variational Autoencoder

Disaster Intensity-Based Selection of Training Samples for Remote Sensing Building Damage Classification

Buildings Classification using Very High Resolution Satellite Imagery

Contact Info

Product

Resources

About