Target Domain Dataset Research Articles

Unsupervised domain adaptation with self-attention for post-disaster building damage detection

Fast assessment of damaged buildings is important for post-disaster rescue operations. Building damage detection leveraging image processing and machine learning techniques has become a popular research focus in recent years. Although supervised learning approaches have made considerable improvement for damaged building assessment, rapidly deploying supervised classification is still difficult due to the complexity in obtaining a large number of labeled samples in the aftermath of disasters. We propose an unsupervised self-attention domain adaptation (USADA) model, which transforms instances of the source domain to those of the target domain in pixel space, to address the aforementioned issue. The proposed USADA consists of three parts: a set of generative adversarial networks (GANs), a classifier, and a self-attention module. The GAN adapts source domain images to ensure their similarity to target domain images. Once adapted, the classifier can be trained using the adapted images along with the original images of the source domain to classify damaged buildings. The self-attention module is introduced to maintain the foreground of the generated images conditioned on source domain images for generating plausible samples. As a case study, aerial images of Hurricane Sandy, Maria, and Irma, are used as the source and target domain datasets in our experiments. Experimental results demonstrate that classification accuracies of 68.1% and 84.1% are achieved, and our method obtains improvements of 2.0% and 3.6% against pixel-level domain adaptation, which is the basis of our model.

Regularized Bayesian transfer learning for population-level etiological distributions.

SummaryComputer-coded verbal autopsy (CCVA) algorithms predict cause of death from high-dimensional family questionnaire data (verbal autopsy) of a deceased individual, which are then aggregated to generate national and regional estimates of cause-specific mortality fractions. These estimates may be inaccurate if CCVA is trained on non-local training data different from the local population of interest. This problem is a special case of transfer learning, i.e., improving classification within a target domain (e.g., a particular population) with the classifier trained in a source-domain. Most transfer learning approaches concern individual-level (e.g., a person’s) classification. Social and health scientists such as epidemiologists are often more interested with understanding etiological distributions at the population-level. The sample sizes of their data sets are typically orders of magnitude smaller than those used for common transfer learning applications like image classification, document identification, etc. We present a parsimonious hierarchical Bayesian transfer learning framework to directly estimate population-level class probabilities in a target domain, using any baseline classifier trained on source-domain, and a small labeled target-domain dataset. To address small sample sizes, we introduce a novel shrinkage prior for the transfer error rates guaranteeing that, in absence of any labeled target-domain data or when the baseline classifier is perfectly accurate, our transfer learning agrees with direct aggregation of predictions from the baseline classifier, thereby subsuming the default practice as a special case. We then extend our approach to use an ensemble of baseline classifiers producing an unified estimate. Theoretical and empirical results demonstrate how the ensemble model favors the most accurate baseline classifier. We present data analyses demonstrating the utility of our approach.

Convolutional Neural Network Coupled with a Transfer-Learning Approach for Time-Series Flood Predictions

East Asian regions in the North Pacific have recently experienced severe riverine flood disasters. State-of-the-art neural networks are currently utilized as a quick-response flood model. Neural networks typically require ample time in the training process because of the use of numerous datasets. To reduce the computational costs, we introduced a transfer-learning approach to a neural-network-based flood model. For a concept of transfer leaning, once the model is pretrained in a source domain with large datasets, it can be reused in other target domains. After retraining parts of the model with the target domain datasets, the training time can be reduced due to reuse. A convolutional neural network (CNN) was employed because the CNN with transfer learning has numerous successful applications in two-dimensional image classification. However, our flood model predicts time-series variables (e.g., water level). The CNN with transfer learning requires a conversion tool from time-series datasets to image datasets in preprocessing. First, the CNN time-series classification was verified in the source domain with less than 10% errors for the variation in water level. Second, the CNN with transfer learning in the target domain efficiently reduced the training time by 1/5 of and a mean error difference by 15% of those obtained by the CNN without transfer learning, respectively. Our method can provide another novel flood model in addition to physical-based models.

An adaptive deep transfer learning method for bearing fault diagnosis

Bearing fault diagnosis has made some achievements based on massive labeled fault data. In practical engineering, machines are mostly in healthy and faults seldom happen, it’s difficult or expensive to collect massive labeled fault data. To solve the problem, an adaptive deep transfer learning method for bearing fault diagnosis is proposed in this paper. Firstly, a long-short term memory recurrent neural network model based on instance-transfer learning is constructed to generate some auxiliary datasets. Secondly, joint distribution adaptation, a feature-transfer learning method, which is used to reduce the differences in probability distributions between an auxiliary dataset and target domain dataset. Finally, grey wolf optimization algorithm is introduced to adaptively learn key parameters of joint distribution adaptation. The proposed method is verified with two kinds of datasets, and the results demonstrate the effectiveness and robustness of the proposed method when the labeled fault data are scarce.

Domain adaptation for semantic role labeling of clinical text.

Semantic role labeling (SRL), which extracts a shallow semantic relation representation from different surface textual forms of free text sentences, is important for understanding natural language. Few studies in SRL have been conducted in the medical domain, primarily due to lack of annotated clinical SRL corpora, which are time-consuming and costly to build. The goal of this study is to investigate domain adaptation techniques for clinical SRL leveraging resources built from newswire and biomedical literature to improve performance and save annotation costs. Multisource Integrated Platform for Answering Clinical Questions (MiPACQ), a manually annotated SRL clinical corpus, was used as the target domain dataset. PropBank and NomBank from newswire and BioProp from biomedical literature were used as source domain datasets. Three state-of-the-art domain adaptation algorithms were employed: instance pruning, transfer self-training, and feature augmentation. The SRL performance using different domain adaptation algorithms was evaluated by using 10-fold cross-validation on the MiPACQ corpus. Learning curves for the different methods were generated to assess the effect of sample size. When all three source domain corpora were used, the feature augmentation algorithm achieved statistically significant higher F-measure (83.18%), compared to the baseline with MiPACQ dataset alone (F-measure, 81.53%), indicating that domain adaptation algorithms may improve SRL performance on clinical text. To achieve a comparable performance to the baseline method that used 90% of MiPACQ training samples, the feature augmentation algorithm required <50% of training samples in MiPACQ, demonstrating that annotation costs of clinical SRL can be reduced significantly by leveraging existing SRL resources from other domains.