Domain Adaptation Algorithm Research Articles

MGFKD: A semi-supervised multi-source domain adaptation algorithm for cross-subject EEG emotion recognition

Currently, most models rarely consider the negative transfer problem in the research field of cross-subject EEG emotion recognition. To solve this problem, this paper proposes a semi-supervised domain adaptive algorithm based on few labeled samples of target subject, which called multi-domain geodesic flow kernel dynamic distribution alignment (MGFKD). It consists of three modules: 1) GFK common feature extractor: projects the feature distribution of source and target subjects to the Grassmann manifold space, and obtains the latent common features of the two feature distributions through GFK method. 2) Source domain selector: obtains pseudo-labels of the target subject through weak classifier, finds "golden source subjects" by using few known labels of target subjects. 3) Label corrector: uses a dynamic distribution balance strategy to correct the pseudo-labels of the target subject. We conducted comparison experiments on the SEED and SEED-IV datasets, and the results show that MGFKD outperforms unsupervised and semi-supervised domain adaptation algorithms, achieving an average accuracy of 87.51±7.68% and 68.79±8.25% on the SEED and SEED-IV datasets with only one labeled sample per video for target subject. Especially when the number of source domains is set as 6 and the number of known labels is set as 5, the accuracy increase to 90.20±7.57% and 69.99±7.38%, respectively. The above results prove that our proposed algorithm can efficiently and quickly improve the cross-subject EEG emotion classification performance. Since it only need a small number of labeled samples of new subjects, making it has strong application value in future EEG-based emotion recognition applications.

Leaf disease detection using deep Convolutional Neural Networks

The automatic recognition of plant diseases is of crucial importance for the current development of agriculture. Fast and efficient identification can greatly reduce the natural, economic, and human resource loss caused to agricultural practitioners. Deep neural networks allow computers to learn plant disease detection in an end-to-end manner, thereby obtaining better results and higher efficiency. While Convolutional Neural Network (CNN) models have become a well-established tool for detecting plant diseases, the lack of robustness of the models due to environmental variations remains to be a critical concern. Recent research into overcoming this challenge includes domain adaptation (DA) algorithms like classic Domain-Adversarial Neural Network (DANN) or the innovative Multi-Representation Subdomain Adaptation Network with Uncertainty Regularization for Cross-Species Plant Disease Classification (MSUN). However, the topic remains under-explored as the newly developed methods were not tested on many crop species and diseases. This research focuses on four deep CNN models (MobileNet, VGG, GoogLenet, and ResNet). The models are developed and tested using the New Plant Diseases dataset on Kaggle, which comprises 70,000+ training images (offline-augmented) and 17,000+ validation images encompassing 38 different classes of healthy and diseased plant leaves. The models would be cross-evaluated upon their accuracy and training speed, as well as their change in performance after optimization and applying DA methods. With an uppermost accuracy of 86.4% in test dataset from the wild, results show that Transfer Learning, Model Ensemble as well as Domain Adaptation works effectively to increase the robustness of models which will ultimately benefit farmers in detecting plant diseases and deciding on the best treatment in real-time.

Heterogeneous Domain Adaptation Framework for Logging Lithofacies Identification

Summary Reservoir lithofacies type is an important indicator of reservoir quality and oiliness, and understanding lithofacies type can help geologists and engineers make informed decisions about exploration and development activities. The use of well-log data to establish machine learning models for lithofacies identification has gained popularity; however, the assumption that data are independent identical distribution followed by these models is often unrealistic. Additionally, there is a possible incompatibility between the training and test data in terms of feature space dimensions. We propose the heterogeneous domain adaptation framework for logging lithofacies identification (HDAFLI) to address these problems. The framework comprises three main contributions: (i) The denoising autoencoder feature mapping (DAFM) module is adopted to resolve the incompatibility issue in feature space between training and test data. The connection between training and test data can be effectively established to improve the performance and generalization ability. (ii) The transferability and discriminative joint probability distribution adaptive (TDJPDA) module addresses the issue of data distribution differences. It improves the transferability of training and test data by minimizing the maximum mean difference (MMD) of the joint probabilities of the source and target domains and enhances their discriminative ability by maximizing the joint probability MMD of different lithofacies categories. (iii) Bayesian optimization is used to optimize hyperparameters in the light gradient boosting machine (LightGBM) model for high computational efficiency in determining the best accuracy. We selected well-logging data from eight wells in the Pearl River Mouth Basin of the South China Sea to design four tasks and compared HDAFLI with various baseline machine learning algorithms and baseline domain adaptive algorithms. The results show that HDAFLI has the highest average accuracy among the four tasks. It is 19.76% and 8.94% higher than the best-performing baseline machine learning algorithm and baseline domain adaptive method among the comparison algorithms, respectively. For HDAFLI, we also conducted ablation experiments, time cost and convergence performance analysis, parameter sensitivity experiments, and feature visualization experiments. The results of ablation experiments show that the three modules of HDAFLI all play an active role, working together to achieve the best results. In addition, HDAFLI has a reasonable time cost, can become stable after several iterations, and has good convergence performance. The results of parameter sensitivity experiments confirm that the accuracy of HDAFLI does not change significantly with changes in hyperparameters, which is robust. The results of feature visualization experiments show that the data of the training set and the test set are concentrated together to a certain extent, which indicates that HDAFLI has completed the task of data distribution alignment very well. The findings of this study can help for a better understanding of how to address the challenge of reservoir lithofacies identification through a heterogeneous domain adaptation framework. By solving the problem of feature space incompatibility and data distribution difference between training data and test data, the application of HDAFLI provides geologists and engineers with more accurate lithofacies classification tools. This study has practical application value for reservoir quality assessment, oiliness prediction, and exploration and development decision-making.

Landmark-Based Domain Adaptation and Selective Pseudo-Labeling for Heterogeneous Defect Prediction

Cross -project defect prediction (CPDP) is a promising technical means to solve the problem of insufficient training data in software defect prediction. As a special case of CPDP, heterogeneous defect prediction (HDP) has received increasing attention in recent years due to its ability to cope with different metric sets in projects. Existing studies have proven that using mixed-project data is a potential way to improve HDP performance, but there remain several challenges, including the negative impact of noise modules and the insufficient utilization of unlabeled modules. To this end, we propose a landmark-based domain adaptation and selective pseudo-labeling (LDASP) approach for mixed-project HDP. Specifically, we propose a novel landmark-based domain adaptation algorithm considering marginal and conditional distribution alignment and a class-wise locality structure to reduce the heterogeneity between both projects while reweighting modules to alleviate the negative impact brought by noise ones. Moreover, we design a progressive pseudo-label selection strategy exploring the underlying discriminative information of unlabeled target data to further improve the prediction effect. Extensive experiments are conducted based on 530 heterogeneous prediction combinations that are built from 27 projects using four datasets. The experimental results show that (1) our approach improves the F1-score and AUC over the baselines by 9.8–20.2% and 4.8–14.4%, respectively and (2) each component of LDASP (i.e., the landmark weights and selective pseudo-labeling strategy) can promote the HDP performance effectively.

Adversarial learning-based domain adaptation algorithm for intracranial artery stenosis detection on multi-source datasets

Intracranial arterial stenosis (ICAS) is characterized by the pathological narrowing or occlusion of the inner lumen of intracranial blood vessels. However, the retina can indirectly react to cerebrovascular disease. Therefore, retinal fundus images (RFI) serve as valuable noninvasive and easily accessible screening tools for early detection and diagnosis of ICAS. This paper introduces an adversarial learning-based domain adaptation algorithm (ALDA) specifically designed for ICAS detection in multi-source datasets. The primary objective is to achieve accurate detection and enhanced generalization of ICAS based on RFI. Given the limitations of traditional algorithms in meeting the accuracy and generalization requirements, ALDA overcomes these challenges by leveraging RFI datasets from multiple sources and employing the concept of adversarial learning to facilitate feature representation sharing and distinguishability learning. In order to evaluate the performance of the ALDA algorithm, we conducted experimental validation on multi-source datasets. We compared its results with those obtained from other deep learning algorithms in the ICAS detection task. Furthermore, we validated the potential of ALDA for detecting diabetic retinopathy. The experimental results clearly demonstrate the significant improvements achieved by the ALDA algorithm. By leveraging information from diverse datasets, ALDA learns feature representations that exhibit enhanced generalizability and robustness. This makes it a reliable auxiliary diagnostic tool for clinicians, thereby facilitating the prevention and treatment of cerebrovascular diseases.

Fault classification of the rolling bearing based on minimax entropy domain adaption augmented with signal generation algorithm

Rolling bearing faults have been capturing substantial research attention as they are the root causes of malfunctions in mechatronics systems than any other factors. The detection of rolling bearing faults in the early stage is therefore a mandatory requirement demanded by reliable industrial plants. To release the dependence of diagnostic methods on human expertise and system’s understanding, this work proposes a fault classification method for rolling bearings that is based on a deep learning framework. The framework consists of a minimax entropy domain adaptation algorithm augmented with a signal generalization algorithm. The function of the signal generalization algorithm is to reduce the domain shift between training and testing datasets that are often obtained experimentally from different working conditions. The generalized signal is then represented in the form of Fourier series whose coefficients contain intrinsic information that associated with different types of bearing faults. A convolutional neural network extracts the hidden information of bearing faults buried in the Fourier coefficients and then categorises the working condition of the bearing under test. By combining the advantages of both signal processing techniques in the frequency domain and the minimax entropy domain adaptation, the novel diagnostic framework is able to detect bearing faults from different working conditions. The effectiveness of the proposed diagnostic algorithm is experimentally verified by two case studies that were prepared with different types and levels of bearing faults.

Graph Domain Adaptation: A Generative View

Recent years have witnessed tremendous interest in deep learning on graph-structured data. Due to the high cost of collecting labeled graph-structured data, domain adaptation is important to supervised graph learning tasks with limited samples. However, current graph domain adaptation methods are generally adopted from traditional domain adaptation tasks, and the properties of graph-structured data are not well utilized. For example, the observed social networks on different platforms are controlled not only by the different crowds or communities but also by domain-specific policies and background noise. Based on these properties in graph-structured data, we first assume that the graph-structured data generation process is controlled by three independent types of latent variables, i.e., the semantic latent variables, the domain latent variables, and the random latent variables. Based on this assumption, we propose a disentanglement-based unsupervised domain adaptation method for the graph-structured data, which applies variational graph auto-encoders to recover these latent variables and disentangles them via three supervised learning modules. Extensive experimental results on two real-world datasets in the graph classification task reveal that our method not only significantly outperforms the traditional domain adaptation methods and the disentangled-based domain adaptation methods but also outperforms the state-of-the-art graph domain adaptation algorithms. The code is available at https://github.com/rynewu224/GraphDA .

Research on Domain Adaptive Object Detection Algorithms Based on Deep Learning

Research on Domain Adaptive Object Detection Algorithms Based on Deep Learning

A Domain Adaptive Few-Shot SAR Ship Detection Algorithm Driven by the Latent Similarity between Optical and SAR Images

A Domain Adaptive Few-Shot SAR Ship Detection Algorithm Driven by the Latent Similarity between Optical and SAR Images

A Domain Adaptive IoT Intrusion Detection Algorithm Based on GWR-GCN Feature Extraction and Conditional Domain Adversary

A Domain Adaptive IoT Intrusion Detection Algorithm Based on GWR-GCN Feature Extraction and Conditional Domain Adversary

Select, Purify, and Exchange: A Multisource Unsupervised Domain Adaptation Method for Building Extraction.

Accurately extracting buildings from aerial images has essential research significance for timely understanding human intervention on the land. The distribution discrepancies between diversified unlabeled remote sensing images (changes in imaging sensor, location, and environment) and labeled historical images significantly degrade the generalization performance of deep learning algorithms. Unsupervised domain adaptation (UDA) algorithms have recently been proposed to eliminate the distribution discrepancies without re-annotating training data for new domains. Nevertheless, due to the limited information provided by a single-source domain, single-source UDA (SSUDA) is not an optimal choice when multitemporal and multiregion remote sensing images are available. We propose a multisource UDA (MSUDA) framework SPENet for building extraction, aiming at selecting, purifying, and exchanging information from multisource domains to better adapt the model to the target domain. Specifically, the framework effectively utilizes richer knowledge by extracting target-relevant information from multiple-source domains, purifying target domain information with low-level features of buildings, and exchanging target domain information in an interactive learning manner. Extensive experiments and ablation studies constructed on 12 city datasets prove the effectiveness of our method against existing state-of-the-art methods, e.g., our method achieves 59.1% intersection over union (IoU) on Austin and Kitsap → Potsdam, which surpasses the target domain supervised method by 2.2% . The code is available at https://github.com/QZangXDU/SPENet.

Uncertainty-Aware Active Domain Adaptive Salient Object Detection.

Due to the advancement of deep learning, the performance of salient object detection (SOD) has been significantly improved. However, deep learning-based techniques require a sizable amount of pixel-wise annotations. To relieve the burden of data annotation, a variety of deep weakly-supervised and unsupervised SOD methods have been proposed, yet the performance gap between them and fully supervised methods remains significant. In this paper, we propose a novel, cost-efficient salient object detection framework, which can adapt models from synthetic data to real-world data with the help of a limited number of actively selected annotations. Specifically, we first construct a synthetic SOD dataset by copying and pasting foreground objects into pure background images. With the masks of foreground objects taken as the ground-truth saliency maps, this dataset can be used for training the SOD model initially. However, due to the large domain gap between synthetic images and real-world images, the performance of the initially trained model on the real-world images is deficient. To transfer the model from the synthetic dataset to the real-world datasets, we further design an uncertainty-aware active domain adaptive algorithm to generate labels for the real-world target images. The prediction variances against data augmentations are utilized to calculate the superpixel-level uncertainty values. For those superpixels with relatively low uncertainty, we directly generate pseudo labels according to the network predictions. Meanwhile, we select a few superpixels with high uncertainty scores and assign labels to them manually. This labeling strategy is capable of generating high-quality labels without incurring too much annotation cost. Experimental results on six benchmark SOD datasets demonstrate that our method outperforms the existing state-of-the-art weakly-supervised and unsupervised SOD methods and is even comparable to the fully supervised ones. Code will be released at: https://github.com/czh-3/UADA.

Domain-Invariant Feature and Generative Adversarial Network Boundary Enhancement for Multi-Source Unsupervised Hyperspectral Image Classification

Hyperspectral image (HIS) classification, a crucial component of remote sensing technology, is currently challenged by edge ambiguity and the complexities of multi-source domain data. An innovative multi-source unsupervised domain adaptive algorithm (MUDA) structure is proposed in this work to overcome these issues. Our approach incorporates a domain-invariant feature unfolding algorithm, which employs the Fourier transform and Maximum Mean Discrepancy (MMD) distance to maximize invariant feature dispersion. Furthermore, the proposed approach efficiently extracts intraclass and interclass invariant features. Additionally, a boundary-constrained adversarial network generates synthetic samples, reinforcing the source domain feature space boundary and enabling accurate target domain classification during the transfer process. Furthermore, comparative experiments on public benchmark datasets demonstrate the superior performance of our proposed methodology over existing techniques, offering an effective strategy for hyperspectral MUDA.

Adversarial unsupervised domain adaptation based on generative adversarial network for stock trend forecasting

Stock trend forecasting, which refers to the prediction of the rise and fall of the next day’s stock price, is a promising research field in financial time series forecasting, with a large quantity of well-performing algorithms and models being proposed. However, most of the studies focus on trend prediction for stocks with a large number of samples, while the trend prediction problem of newly listed stocks with only a small number of samples is neglected. In this work, we innovatively design a solution to the Small Sample Size (SSS) trend prediction problem of newly listed stocks. Traditional Machine Learning (ML) and Deep Learning (DL) techniques are based on the assumption that the available labeled samples are substantial, which is invalid for SSS trend prediction of newly listed stocks. In order to break out of this dilemma, we propose a novel Adversarial Unsupervised Domain Adaptation Network (AUDA-Net), based on Generative Adversarial Network (GAN), ad hoc for SSS stock trend forecasting. Different from the traditional domain adaptation algorithms, we employ a GAN model, which is trained on basis of the target stock dataset, to effectively solve the absence problem of available samples. Notably, AUDA-Net can reasonably and successfully transfer the knowledge learned from the source stock dataset to the newly listed stocks with only a few samples. The stock trend forecasting performance of our proposed AUDA-Net model has been verified through extensive experiments conducted on several real stock datasets of the U.S. stock market. Using stock trend forecasting as a case study, we show that the SSS forecasting results produced by AUDA-Net are favorably comparable to the state-of-the-art.

Towards More General Loss and Setting in Unsupervised Domain Adaptation

In this paper, we present an analysis of unsupervised domain adaptation with a series of theoretical and algorithmic results. We derive a novel Rényi- <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\alpha$</tex-math></inline-formula> divergence-based generalization bound, which is tailored to domain adaptation algorithms with arbitrary loss functions in a stochastic setting. Moreover, our theoretical results provide new insights into the assumptions for successful domain adaptation: the closeness between the conditional distributions of the domains and the Lipschitzness on the source domain. With these assumptions, we reveal the following: if their conditional generation distributions are close, the Lipschitzness property of the target domain can be transferred from the Lipschitzness on the source domain, without knowing the exact target distribution. Motivated by our analysis and assumptions, we further derive practical principles for deep domain adaptation: 1) Rényi-2 adversarial training for marginal distributions matching and 2) Lipschitz regularization for the classifier. Our experimental results on both synthetic and real-world datasets support our theoretical findings and the practical efficiency of the proposed principles.

Visualization of concrete internal defects based on unsupervised domain adaptation algorithm for transfer learning of experiment-simulation hybrid dataset of impact echo signals

Detecting concrete internal defects through deep learning analysis of impact echo signals faces two challenges: (1) the traditional signal processing method such as wavelet transform (WT) fails to reflect data-sensitive damage characteristics due to the uncertainty principle and (2) the limited labeled data acquired from real structures impedes network training. To address the first challenge, this paper proposes the WT-based synchrosqueezing transform (WT-SST) for the conversion of time-series data to the time-frequency spectrogram, which can provide effective features for the network in time and frequency domains simultaneously. To overcome the second challenge, numerical simulation data are supplemented for the augment of labeled data. To minimize the effect of data variance between experiments and simulations, this paper uses an unsupervised domain adaptation (DA) network for the transfer training of labeled simulation data (original domain) and unlabeled experimental data (target domain). The DA network extracts domain-invariant features by maximizing the domain recognition error and minimizing the probability distribution distance. The damage probability is calculated by the trained model to produce a 2D defect contour image of concrete specimens, and the three-dimensional visualization of internal defects by estimating the defect depth based on the defect area of contour image. Finally, the recognition precision, recall, F1-score, and accuracy of the model of unsupervised DA network trained by a hybrid dataset reaches 89.4%, 88.4%, 88.9%, and 94.7%, respectively.

A CSI Dataset for Wireless Human Sensing on 80 MHz Wi-Fi Channels

In the last years, several machine learning-based techniques have been proposed to monitor human movements from Wi-Fi channel readings. However, the development of domain-adaptive algorithms that robustly work across different environments is still an open problem, whose solution requires large datasets characterized by strong domain diversity, in terms of environments, persons andWi-Fi hardware. To date, the few public datasets available are mostly obsolete - as obtained via Wi-Fi devices operating on 20 or 40 MHz bands - and contain little or no domain diversity, thus dramatically limiting the advancements in the design of sensing algorithms. The present contribution aims to fill this gap by providing a dataset of IEEE 802.11ac channel measurements over an 80 MHz bandwidth channel featuring notable domain diversity, through measurement campaigns that involved thirteen subjects across different environments, days, and with different hardware. Novel experimental data is provided by blocking the direct path between the transmitter and the monitor, and collecting measurements in a semi-anechoic chamber (no multi-path fading). Overall, the dataset - available on IEEE DataPort [1] - contains more than thirteen hours of channel state information readings (23.6 GB), allowing researchers to test activity/identity recognition and people counting algorithms.

Improving generalisability and transferability of machine-learning-based maize yield prediction model through domain adaptation

Modern problems in agricultural management require non-traditional solutions, one of which is by utilizing domain adaptive machine learning models for crop yield prediction which are able to perform reliably in different temporal or spatial domains. However, most studies have focused on the application of domain adaptation to classification tasks such as crop type identification, while the application to regression tasks such as crop yield prediction have been limited. In this study, we explore the generalisability and transferability of ordinary Deep Neural Network (DNN) and domain adaptive neural network models created using three domain adaptation algorithms, namely Discriminative Adversarial Neural Network (DANN), Kullback-Leibler Importance Estimation Procedure (KLIEP), and Regular Transfer Neural Network (RTNN). These three algorithms represent feature-based, instance-based, and parameter-based domain adaptations, respectively. Maize yield records, weather variables, and remotely sensed features from 11 states in the US corn belt acquired in 2006–2020 were compiled and segregated into classes according to temporal (year) and spatial characteristics (annual growing degree days [GDD], vapor pressure deficit [VPD], soil organic content [SOC], and green chlorophyll vegetation index/GCI). We found that models trained using datasets from temperate regions with medium-high GDD and moderate VPD perform well whereas SOC does not significantly affect the generalisability. It is not advisable to train models with datasets constrained by GCI as this feature correlates significantly with the maize yield, and adaptation between two domains that rarely intercept will not work well. We also demonstrate that Kullback-Leibler divergence computed using features from source and target domains can be used to justify the feasibility of domain adaptation. Based on the divergence, a model trained in the US (or another region with sufficient data) is expected to work reliably in other regions through domain adaptation, especially feature-based adaptation.

Discrepancy-Guided Domain-Adaptive Data Augmentation.

Data augmentation has been observed playing a crucial role in achieving better generalization in many machine learning tasks, especially in unsupervised domain adaptation (DA). It is particularly effective on visual object recognition tasks as images are high-dimensional with an enormous range of variations that can be simulated. Existing data augmentation techniques, however, are not explicitly designed to address the differences between different domains. Expert knowledge about the data is required, as well as manual efforts in finding the optimal parameters. In this article, we propose a novel domain-adaptive augmentation method by making use of a state-of-the-art style transfer method and domain discrepancy measurement. Specifically, we measure the discrepancy between source and target domains, and use it as a guide to augment the original source samples using style transferred source-to-target samples. The proposed domain-adaptive augmentation method is data and model agnostic that can be easily incorporated with state-of-the-art DA algorithms. We show empirically that, by using this domain-adaptive augmentation, we are able to gradually reduce the discrepancy between the source and target samples, and further boost the adaptation performance using different DA algorithms on three popular domain adaption datasets.

Conformal Test Martingale-Based Change-Point Detection for Geospatial Object Detectors

Unsupervised domain adaptation for object detectors addresses the problem of improving the cross-domain robustness of object detection from label-rich to label-poor domains, which has been explored in many studies. However, one important issue in terms of when to apply the domain adaptation algorithm for geospatial object detectors has not been fully considered in the literature. In this paper, we tackle the problem of detecting the moment or change-point when the domain of geospatial images changes based on conformal test martingale. Beyond the simple introduction of this martingale-based process, we also propose a novel transformation approach to the original conformal test martingale to make change-point detection more efficient. The experiments are conducted with two partitions of our released large-scale remote sensing dataset and the experimental results empirically demonstrate the promising effectiveness and efficiency of our proposed algorithms for change-point detection.