Multi-source Domain Research Articles

Dynamic Classifier Alignment for Unsupervised Multi-Source Domain Adaptation

Unsupervised domain adaptation leverages the previously gained knowledge from a labeled source domain to tackle the task from a different but similar unlabeled target domain. Most existing methods focus on transferring knowledge from a single source domain, but the information from a single domain may be inadequate to complete the target task. Some previous studies have turned to multi-view representations to enrich the transferable information. However, they simply concatenate multi-view features, which may result in information redundancy. In this paper, we propose a dynamic classifier alignment (DCA) method for multi-source domain adaptation, which aligns classifiers driven from multi-view features via a sample-wise automatic way. As proposed, both the importance of each view and the contribution of each source domain are investigated. To determine the important degrees of multiple views, an importance learning function is built by generating an auxiliary classifier. To learn the source combination parameters, a domain discriminator is developed to estimate the probability of a sample belonging to multiple source domains. Meanwhile, a self-training strategy is proposed to enhance the cross-domain ability of source classifiers with the assistance of pseudo target labels. Experiments on real-world visual datasets show the superiority of the proposed DCA.

Multi-Source Domain Adaptation and Fusion for Speaker Verification

Multi-Source Domain Adaptation and Fusion for Speaker Verification

Multisource Domain Transfer Learning Based on Spectral Projections for Hyperspectral Image Classification

Hyperspectral image classification is an important topic for hyperspectral remote sensing with various applications. Hyperspectral image classification accuracy has been greatly improved with the introduction of deep neural networks, while the idea of transfer learning provides an opportunity to solve the problem even with the lack of training samples. In this paper, we propose an effective transfer learning approach for hyperspectral images, projecting hyperspectral images with different sensors and different number of bands into a general spectral space, preserving the relative positions of each band for spectral alignment, and designing a hierarchical depth neural network for shallow feature transfer and deep feature classification. The experiments show that the proposed method can effectively preserve the source domain features, especially for the scenarios with very few samples in the target domain, which can significantly improve the classification accuracy and reduce the risk of model overfitting. Meanwhile, this strategy greatly reduces the requirement of source domain data, using multi-sensor data to jointly train a more robust general feature model. The proposed method can achieve high accuracies even with few training samples compared to currently many state-of-the-art classification methods.

Learn Generalized Features Via Multi-Source Domain Adaptation: Intelligent Diagnosis Under Variable/Constant Machine Conditions

A primary goal of fault diagnosis is to build generalizable models for flexible industrial scenes. However, most literature assumed that the training and testing data are collected from the same distributions, which poses obstacles in cross-domain diagnosis. This paper proposes a multi-source domain adaptation (MSDA) strategy in response to diversiform working conditions, in which the labeled testing data are difficult to obtain. The regularization term expressed by multi-order moment matching is adopted to extract transferable knowledge from multiple source domains. An adversarial strategy, which takes the maximization and minimization of two independent classifiers’ discrepancy as the alternate optimization objective, is introduced to dynamically align moments of feature distributions between all domain pairs. Three datasets are carried out to prove the robustness of the proposed method. The results of comparative experiments and ablation study demonstrate that the approach can learn features from multiple specific domains and possess strong generalization ability under diverse constant or any unknown variable conditions with unlabeled target samples.

Pseudo Label Rectification via Co-Teaching and Decoupling for Multisource Domain Adaptation in Semantic Segmentation

Multi-source Unsupervised Domain Adaptation (MUDA) is an approach aiming to transfer the knowledge obtained from multiple labeled source domains to an unlabeled target domain. In this paper, we propose a novel self-training method for MUDA, which includes pseudo label-oriented coteaching and pseudo label decoupling that are attempted for the pseudo label rectification-based MUDA for semantic segmentation. Existing ensemble-based self-training methods which are well-known approaches for MUDA use pseudo labels made from the ensemble of the predictions of multiple models to transfer the knowledge of source domains to the target domain. In these methods, information from multiple models can be contaminated, or errors from incorrect pseudo labels can be propagated. On the other hand, the proposed pseudo label-oriented coteaching trains multiple models by using pseudo labels from the peer model without any integration of pseudo labels. Simultaneously, the pseudo label decoupling method is proposed for rectification of pseudo labels, which updates the models with two pseudo labels only if they disagree. It also alleviates the problem of class imbalance in semantic segmentation, in which dominant classes lead the update for training. The effects of the proposed pseudo label-oriented coteaching and pseudo label decoupling on the performance of semantic segmentation were verified by extensive experiments. The proposed method achieved the best semantic segmentation accuracy compared with the benchmark methods. In addition, we confirmed that the prediction accuracy of small objects was greatly improved by the proposed pseudo label rectification.

Moment matching-based intraclass multisource domain adaptation network for bearing fault diagnosis

Deep learning based fault diagnosis methods assume that training and testing data with sufficient labels are available and share a same distribution. In practical scenarios, this assumption does not generally hold due to variable working conditions of rotating machineries and the difficulty in labeling vibration data under all working conditions. Transfer learning (TL) overcomes this problem by utilizing knowledge learned from the source domain to help accomplish tasks on the target domain. Although TL based fault diagnosis has been considerably studied, most studies mainly focus on single-source TL. Since multisource domains with labeled samples from which more useful knowledge can be extracted are available, in this paper, a novel multisource TL model, called the moment matching-based intraclass multisource domain adaptation network, is proposed. This model uses a feature learner to generate features of each source and target domain data to enable the joint weight classifier to predict target labels. It also introduces a moment matching-based distance metric to reduce the distance among all source domains and the target domain. During the training of the model, an intraclass alignment training strategy is applied to match the marginal and conditional distributions of each domain simultaneously. Experiments on two datasets are performed, wherein the proposed method is used to identify bearing fault types under four load conditions. Experiment results, such as high diagnostic accuracies support the reliability and generalizability of the proposed model.

Multisource Domain Adaption for Health Degradation Monitoring of Lithium-Ion Batteries

Battery health monitoring is crucial to reduce unexpected maintenance and realize maximum productivity. However, batteries generally work under dynamic and complex working conditions (i.e., different domains) in industrial applications. The distribution difference exists not only between source and target domain but also between multisource domains, it is a challenging problem to monitor battery health deterioration under multiple working conditions. This study proposes a novel transfer learning-based method, multisource domain adaption network (MSDAN), to address the problem of battery health degradation monitoring under different working conditions. First, a battery health degradation monitoring method is proposed based on multisource transfer learning. The knowledge learned from multiple operational conditions is transferred to the target condition. Second, multisource domain adaption is proposed to address the problem of distribution discrepancy of different domains, where unsupervised feature alignment metric and maximum mean discrepancy (MMD) are utilized to evaluate the difference between target domain and each source domain. Multisource adversarial learning is adopted to guide feature generator to provide domain-invariant features of different domains. Third, a feature generator is proposed to extract common and domain-specific features of different domains. The experimental results illustrate that MSDAN has a better performance of battery health prognostics than other single-source domain adaption methods.

A Two-Way alignment approach for unsupervised multi-Source domain adaptation

Domain adaptation aims at transferring knowledge from labeled source domain to unlabeled target domain. Current advances primarily concern single source domain and neglect the setting of multiple source domains. Previous unsupervised multi-source domain adaptation (MDA) algorithms only consider domain-level alignment, while neglecting the category-level information among multiple domains and the instance variations inside each domain. This paper introduces a Two-Way alignment framework for MDA (TWMDA), which considers both domain-level and category-level alignments, and addresses the instance variations. We first align the target and multiple sources on the domain-level by an adversarial learning process. To circumvent the drawbacks of adversarial learning, we further reduce the domain gap on the category-level by minimizing the distance between the category prototypes and unlabeled target instances. To address the instance variations, we design an instance weighting strategy for diverse source instances. The effectiveness of TWMDA is demonstrated on three benchmark datasets for image classification.

MCSP-SSS: A Domain Adaptive Framework for High-Accuracy Sensor Data Classification

Due to sensor drift, instrumental variation, or change of measurement object, the distributions of the datasets (domains) acquired by the sensors are often different. A domain adaptive framework called MCSP-SSS is proposed to reduce the distribution discrepancy across domains for high-accuracy sensor data classification. The framework consists of two key parts: Multi-Constraint Subspace Projection (MCSP) and Source Sample Selection (SSS). MCSP is a subspace-projection-based approach, which introduces four constraints to get an optimized projection matrix: Principal Component Analysis (PCA) is used to reduce the redundancy of features; Mean Distribution Discrepancy (MDD) is applied to minimize the difference between source and target data; Hilbert-Schmidt Independence Criterion (HSIC) is adopted to maximizing the dependence between features and labels; A so-called weighted-within-class scatter matrix is introduced to minimize the within-class variance to avoid samples with different labels to overlap in the subspace. SSS is designed to remove the outliers in projected source samples so as to reduce distribution discrepancy between the source and target samples projected by MCSP. Experimental results show that our framework can achieve the best accuracies in all classification tasks in comparison with other state-of-the-art approaches. The accuracy of MCSP-SSS is 3.57 percentage points (pps) higher on average than that of the second best approach for single-source domain adaptation, and 7.00 pps for multi-source domain adaptation. Source code is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/threedteam/tsc_subspace_projection</uri> .

Multi-Source Domain Adaptation in Sentiment Analysis using Optimized Neural Network and Cross-Domain Semantic Library

Multi-Source Domain Adaptation in Sentiment Analysis using Optimized Neural Network and Cross-Domain Semantic Library

A multisource domain adaptation method for quality prediction in small-batch production systems

Quality prediction for small-batch production processes is a complex problem due to limitations in available training samples. In this study, a multisource domain adaptation joint-Y partial least square (PLS) method is proposed to learn the similarities between domains and use them to construct a quality prediction model. Without constraints on the number of source and target domains, the proposed method can transfer more historical information for the in-operation process than traditional methods. Numerical experiments and a real-world case study of quality prediction in computer wafer production are performed to verify the effectiveness of the proposed method. The results show that the prediction accuracy of the proposed method is high in cases with few training samples in the target domain compared to the accuracies of the joint-Y PLS model and the traditional PLS model.

Label-Based Alignment Multi-Source Domain Adaptation for Cross-Subject EEG Fatigue Mental State Evaluation.

Accurate detection of driving fatigue is helpful in significantly reducing the rate of road traffic accidents. Electroencephalogram (EEG) based methods are proven to be efficient to evaluate mental fatigue. Due to its high non-linearity, as well as significant individual differences, how to perform EEG fatigue mental state evaluation across different subjects still keeps challenging. In this study, we propose a Label-based Alignment Multi-Source Domain Adaptation (LA-MSDA) for cross-subject EEG fatigue mental state evaluation. Specifically, LA-MSDA considers the local feature distributions of relevant labels between different domains, which efficiently eliminates the negative impact of significant individual differences by aligning label-based feature distributions. In addition, the strategy of global optimization is introduced to address the classifier confusion decision boundary issues and improve the generalization ability of LA-MSDA. Experimental results show LA-MSDA can achieve remarkable results on EEG-based fatigue mental state evaluation across subjects, which is expected to have wide application prospects in practical brain-computer interaction (BCI), such as online monitoring of driver fatigue, or assisting in the development of on-board safety systems.

Multi-source unsupervised domain adaptation for object detection

Domain adaptation for object detection has been extensively studied in recent years. Most existing approaches focus on single-source unsupervised domain adaptive object detection. However, a more practical scenario is that the labeled source data is collected from multiple domains with different feature distributions. The conventional approaches do not work very well since multiple domain gaps exist. We propose a Multi-source domain Knowledge Transfer (MKT) method to handle this situation. First, the low-level features from multiple domains are aligned by learning a shallow feature extraction network. Then, the high-level features from each pair of source and target domains are aligned by the followed multi-branch network. After that, we perform two parts of information fusion: (1) We train a detection network shared by all branches based on the transferability of each source sample feature. The transferability of a source sample feature means the indistinguishable degree to the target domain sample features. (2) For using our model, the target sample features output by the multi-branch network are fused based on the average transferability of each domain. Moreover, we leverage both image-level and instance-level attention to promote positive cross-domain transfer and suppress negative transfer. Our main contributions are the two-stage feature alignments and information fusion. Extensive experimental results on various transfer scenarios show that our method achieves the state-of-the-art performance.

A multi-source ensemble domain adaptation method for rotary machine fault diagnosis

Transfer learning has good ability to transfer knowledge for fault diagnosis under different working condition, while domain mismatches or domain shift can still occur during single-source domain transfer fault diagnosis. To alleviate the problem, a multi-source ensemble domain adaptation method is proposed for rotary machinery fault diagnosis. Firstly, multi-source and target domain anchor adapters are constructed based on class-central samples from multi-source domain. Secondly, multi-source ensemble domain adaptation transfer fault diagnosis model considering the mutual difference between multi-source domain is established to obtain multiple classifiers and prediction results. Then the classifiers with good performance are integrated to achieve final diagnosis model and results by ensemble of anchor adapters. Finally, the performance of the proposed method is verified by two experiments. The results show that the proposed method has ability to learn more comprehensive and general domain invariant diagnosis knowledge, significant diagnosis performance and robustness than other transfer learning methods.

Automatic online multi-source domain adaptation

Knowledge transfer across several streaming processes remain challenging problem not only because of different distributions of each stream but also because of rapidly changing and never-ending environments of data streams. Albeit growing research achievements in this area, most of existing works are developed for a single source domain which limits its resilience to exploit multi-source domains being beneficial to recover from concept drifts quickly and to avoid the negative transfer problem. An online domain adaptation technique under multi-source streaming processes, namely automatic online multi-source domain adaptation (AOMSDA), is proposed in this paper. The online domain adaptation strategy of AOMSDA is formulated under a coupled generative and discriminative approach of denoising autoencoder (DAE) where the central moment discrepancy (CMD)-based regularizer is integrated to handle the existence of multi-source domains thereby taking advantage of complementary information sources. The asynchronous concept drifts taking place at different time periods are addressed by a self-organizing structure and a node re-weighting strategy. Our numerical study demonstrates that AOMSDA is capable of outperforming its counterparts in 5 of 8 study cases while the ablation study depicts the advantage of each learning component. In addition, AOMSDA is general for any number of source streams. The source code of AOMSDA is shared publicly inhttps://github.com/Renchunzi-Xie/AOMSDA.git.

Universal multi-Source domain adaptation for image classification

Unsupervised domain adaptation (DA) enables intelligent models to learn transferable knowledge from a labeled source domain and adapt to a similar but unlabeled target domain. Studies showed that knowledge could be transferred from one source domain to another unknown target domain, called Universal DA (UDA). However, there is often more than one source domain in the real-world application to be exploited for DA. In this paper, we formally propose a more general domain adaptation setting for image classification, universal multi-source DA (UMDA), where the label sets of multiple source domains can be different, and the label set of the target domain is completely unknown. The main challenge in UMDA is to identify the common label set among each source and target domain and keep the model scalable as the number of source domains increases. In the face of this challenge, we propose a universal multi-source adaptation network (UMAN) to solve the DA problem without increasing the complexity of the model in various UMDA settings. In UMAN, the reliability of each known class belonging to the common label set is estimated via a novel pseudo-margin vector and its weighted form, which helps adversarial training better align the distributions of multiple source domains and target domain. Moreover, the theoretical guarantee for UMAN is also provided. Massive experimental results show that existing UDA and multi-source DA (MDA) methods cannot be directly deployed to UMDA, and the proposed UMAN achieves the state-of-the-art performance in various UMDA settings.

P3-MSDA: Multi-Source Domain Adaptation Network for Dynamic Visual Target Detection.

Single-trial electroencephalogram detection has been widely applied in brain-computer interface (BCI) systems. Moreover, an individual generalized model is significant for applying the dynamic visual target detection BCI system in real life because of the time jitter of the detection latency, the dynamics and complexity of visual background. Hence, we developed an unsupervised multi-source domain adaptation network (P3-MSDA) for dynamic visual target detection. In this network, a P3 map-clustering method was proposed for source domain selection. The adversarial domain adaptation was conducted for domain alignment to eliminate individual differences, and prediction probabilities were ranked and returned to guide the input of target samples for imbalanced data classification. The results showed that individuals with a strong P3 map selected by the proposed P3 map-clustering method perform best on the source domain. Compared with existing schemes, the proposed P3-MSDA network achieved the highest classification accuracy and F1 score using five labeled individuals with a strong P3 map as the source domain. These findings can have a significant meaning in building an individual generalized model for dynamic visual target detection.

Multi-EPL: Accurate multi-source domain adaptation.

Given multiple source datasets with labels, how can we train a target model with no labeled data? Multi-source domain adaptation (MSDA) aims to train a model using multiple source datasets different from a target dataset in the absence of target data labels. MSDA is a crucial problem applicable to many practical cases where labels for the target data are unavailable due to privacy issues. Existing MSDA frameworks are limited since they align data without considering labels of the features of each domain. They also do not fully utilize the target data without labels and rely on limited feature extraction with a single extractor. In this paper, we propose Multi-EPL, a novel method for MSDA. Multi-EPL exploits label-wise moment matching to align the conditional distributions of the features for the labels, uses pseudolabels for the unavailable target labels, and introduces an ensemble of multiple feature extractors for accurate domain adaptation. Extensive experiments show that Multi-EPL provides the state-of-the-art performance for MSDA tasks in both image domains and text domains, improving the accuracy by up to 13.20%.

Source-free unsupervised multi-source domain adaptation via proxy task for person re-identification

Source-free unsupervised multi-source domain adaptation via proxy task for person re-identification

Multisource domain factorization network for cross-domain fault diagnosis of rotating machinery: An unsupervised multisource domain adaptation method

Unsupervised domain adaptation (DA) provides a promising approach for tackling fault diagnosis tasks of target datasets without labeled data and has been actively studied in recent years. Most of them focus only on single-source DA, compared to multisource DA (MDA), which has remarkable advantages in generalized knowledge learning and generalization performance. Nevertheless, there are very few fault diagnosis studies based on MDA, and it remains challenging to reduce multiple domain shifts to improve diagnostic performance and mitigate negative transfer during learning. To this end, a novel unsupervised MDA-based transfer learning approach called multisource domain factorization network (MDFN) is proposed in this paper, where the generalized diagnosis knowledge is learned from multiple sources and then used for diagnosing the target task. The highlights of MDFN are that the shared-space component analysis and transferability-based entropy penalty strategy are employed to significantly mitigate negative transfer from the two levels of feature representation and instance transferability and effectively learn shared feature representation. Therefore, the MDFN can extract shared features that combine domain-invariance and discriminability, thereby performing better. The results of two experimental cases on six datasets, including cross-operating-condition and cross-component diagnosis tasks, validate the effectiveness and superiority of the proposed method.