Multi-source Domain Adaptation Research Articles

Multi-source partial domain adaptation method based on pseudo-balanced target domain for fault diagnosis

Multisource domain adaptation (MSDA) for fault diagnosis enables knowledge transfer from multisource domains to unknown target domains, which is crucial for enhancing equipment reliability and safety. However, current MSDA methods face two major challenges: (1) they face serious domain-shift problems not only between the target and source domains, but also between different source domains, and (2) in practical applications, class labels in the target domain are likely to be subsets of class labels in the source domain. Therefore, this study considers a setting called multisource partial domain adaptation (MSPDA). A two-stage intelligent fault diagnosis method for MSPDA based on pseudo-balanced target domains (PBTD) is proposed. In the first stage, we propose a weighted adversarial partial domain adaptation method based on a dual progressive strategy that aligns each source domain with the target domain to construct a series of PBTD. In the second stage, an alternating learning scheme is utilized to align the remaining source domains with the PBTDs, which makes full use of multisource information to bridge the discrepancies between different domains. Additionally, this study proposes a multiscale convolutional neural network based on a three-branch attention mechanism that captures the cross-dimensional interactions of scale, channel, and space to enhance the algorithmic characterization capability. Finally, extensive experiments with gear and bearing datasets are conducted to validate the effectiveness of the proposed method.

Unsupervised multi-source domain adaptation for person re-identification via feature fusion and pseudo-label refinement

The objective of unsupervised domain adaptation (UDA) for person re-identification (re-ID) is to associate person in images captured from heterogeneous camera perspectives. Currently, mainstream UDA methods for person re-ID are mainly conducted in single-source and single-target domain scenarios. Moreover, most of these methods do not take the repercussions of pseudo-label noise on model performance into consideration. Therefore, we put forward an unsupervised multi-source domain adaptation (UMDA) method for person re-ID via feature fusion and pseudo-label refinement. Firstly, our method is designed for scenarios where there exist several source domains and only one target domain. We suggest using feature fusion techniques to minimize the domain disparity among the source domains, and employ pseudo-label refinement techniques to ameliorate the ramifications of label noise on model predictions. To substantiate the effectiveness of the recommended methodology, we carry out a succession of experiments on multiple datasets. The advantage and preeminence of our proposed method can be manifested by the experimental outcomes.

Attention Cycle-consistent universal network for More Universal Domain Adaptation

Existing Universal Domain Adaptation (UniDA) approaches can handle various domain adaptation (DA) tasks, which need no prior information about the category overlap across target and source domains. However, traditional UniDA scenario cannot fully cover every DA scenario, e.g., Multi-Source DA is absent. Therefore, aiming to simultaneously handle more DA scenarios in nature, we propose the More Universal Domain Adaptation (MUniDA) task. There are three challenges in MUniDA: (i) Category shift between source and target domains; (ii) Domain shift, especially the domain shift among multiple modalities in the source, which is ignored by the current UniDA approaches; (iii) How to recognize common categories across domains? We propose a more universally applicable DA approach that can tackle above challenges without any modification called Attention Cycle-consistent Universal Network (A-CycleUN). We show through extensive experiments on several benchmarks that A-CycleUN works stably and outperforms baselines across different MUniDA settings.

Multi-source information joint transfer diagnosis for rolling bearing with unknown faults via wavelet transform and an improved domain adaptation network

Recently, unsupervised domain adaptation fault diagnosis (FD) techniques, which learn transferable features by reducing distribution inconsistency of source and target domians, have gained abundant attention and greatly promoted the reliability of rolling bearing (RB) under variable operating conditions. However, open-set domain adaptation issues which contain unknown faults in the test set have not been well addressed. This paper presents a new semi-supervised FD method for RB by combining wavelet transform and an improved domain adaptation network. First, a multi-source domain adaptation network is proposed to extract rich transfer features and achieve complementary information from multiple sources. Then, a pseudo-margin vector is employed to handle unseen faults in the target domain and realize the accurate fault diagnosis of RB. Finally, a new loss function is designed by adding weights to the traditional maximum mean difference to make the common label set more compatible and combining a dynamic optimization strategy to adaptively update the loss of each part. Finally, two experiments indicate our proposed approach has a higher diagnosis accuracy and can effectively tackle the diagnosis issue of unseen faults across different working conditions.

Unsupervised multi-source domain adaptation for person re-identification via sample weighting

The aim of unsupervised domain adaptation (UDA) in person re-identification (re-ID) is to develop a model that can identify the same individual across different cameras in the target domain, using labeled data from the source domain and unlabeled data from the target domain. However, existing UDA person re-ID methods typically assume a single source domain and a single target domain, and seldom consider the scenario of multiple source domains and a single target domain. In the latter scenario, differences in sample size between domains can lead to biased training of the model. To address this, we propose an unsupervised multi-source domain adaptation person re-ID method via sample weighting. Our approach utilizes multiple source domains to leverage valuable label information and balances the inter-domain sample imbalance through sample weighting. We also employ an adversarial learning method to align the domains. The experimental results, conducted on four datasets, demonstrate the effectiveness of our proposed method.

A Unified Framework for Adversarial Attacks on Multi-Source Domain Adaptation

A Unified Framework for Adversarial Attacks on Multi-Source Domain Adaptation

MS-FRAN: A Novel Multi-Source Domain Adaptation Method for EEG-Based Emotion Recognition.

Electroencephalogram (EEG), an important physiological signal, has been widely applied in many fields. Among them, EEG-based emotion recognition has gradually become a research hotspot. However, the large distribution differences and variations of EEG signals across subjects make the current research on emotion recognition stuck in a dilemma. In order to resolve this problem, we choose the domain adaptation methodology to explore the inspiration for solutions. In this paper, a Multi-Source Feature Representation and Alignment Network (MS-FRAN) is proposed, in which a new feature learning module named Wide Feature Extractor (WFE) has been designed. The MS-FRAN adopts and improves the strategy of existing multi-source domain adaptation, which possesses two main benefits. For one thing, it can align the distribution of each pair of source and target domains. For another, it can also reduce the distributional differences among the multiple source domains. To demonstrate the effectiveness of MS-FRAN, we have carried out cross-subject experiments on two public benchmark datasets, SEED and DEAP. Experimental results have shown that our method outperforms the related competitive approaches with greater performance for EEG-based emotion recognition.

Single-/Multi-Source Domain Adaptation via domain separation: A simple but effective method

Domain adaptation (DA) aims to reduce knowledge gap between domains and improve the prediction ability of models in the target domain. However, the representations learned from feature extraction network often contain redundant information, which is harmful to domain alignment. In addition, many methods only focus on either single-source DA task or multi-source DA task, which limits their real-world applications. In this paper, we propose a simple but effective method called Category and Domain Features Augmentation (CDFA), which consists of two components: Contrastive Classifier Network (CCN) and Domain-specific Learning Network (DSLN). CDFA can remove the specific representation at the feature extraction stage to alleviate transfer difficulty, where CCN is used to increase the probabilistic output of samples and avoid misclassification, and DSLN facilitates the separation of redundant information from all representations by learning domain-specific representations. Empirical evaluations on several cross-domain benchmarks under single-source and multi-source DA scenarios illustrate the competitive performance of CDFA with respect to the state-of-the-art.

Multi-Source Video Domain Adaptation With Temporal Attentive Moment Alignment Network

Multi-Source Domain Adaptation (MSDA) is a more practical domain adaptation scenario in real-world scenarios, which relaxes the assumption in conventional Unsupervised Domain Adaptation (UDA) that source data are sampled from a single domain and match a uniform data distribution. The MSDA is more challenging due to the existence of different domain shifts between distinct domain pairs. When considering videos, the negative transfer would be provoked by spatial-temporal features and can be formulated into a more challenging Multi-Source Video Domain Adaptation (MSVDA) problem. In this paper, we address the MSVDA problem by proposing a novel Temporal Attentive Moment Alignment Network (TAMAN) which aims for effective feature transfer by dynamically aligning both spatial and temporal feature moments. The TAMAN further constructs robust global temporal features by attending to dominant domain-invariant local temporal features with high local classification confidence and low disparity between global and local feature discrepancies. To facilitate future research on the MSVDA problem, we introduce comprehensive benchmarks, covering extensive MSVDA scenarios. Empirical results demonstrate a superior performance of the proposed TAMAN across multiple MSVDA benchmarks.

Dual consistent pseudo label generation for multi-source domain adaptation without source data for medical image segmentation.

Unsupervised domain adaptation (UDA) aims to adapt a model learned from the source domain to the target domain. Thus, the model can obtain transferable knowledge even in target domain that does not have ground truth in this way. In medical image segmentation scenarios, there exist diverse data distributions caused by intensity in homogeneities and shape variabilities. But multi source data may not be freely accessible, especially medical images with patient identity information. To tackle this issue, we propose a new multi-source and source-free (MSSF) application scenario and a novel domain adaptation framework where in the training stage, we only get access to the well-trained source domain segmentation models without source data. First, we propose a new dual consistency constraint which uses domain-intra and domain-inter consistency to filter those predictions agreed by each individual domain expert and all domain experts. It can serve as a high-quality pseudo label generation method and produce correct supervised signals for target domain supervised learning. Next, we design a progressive entropy loss minimization method to minimize the class-inter distance of features, which is beneficial to enhance domain-intra and domain-inter consistency in turn. Extensive experiments are performed for retinal vessel segmentation under MSSF condition and our approach produces impressive performance. The sensitivity metric of our approach is highest and it surpasses other methods with a large margin. It is the first attempt to conduct researches on the retinal vessel segmentation task under multi-source and source-free scenarios. In medical applications, such adaptation method can avoid the privacy issue. Furthermore, how to balance the high sensitivity and high accuracy need to be further considered.

A Multisource Domain Adaptation Network for Process Fault Diagnosis Under Different Working Conditions

Transfer learning-based process fault diagnosis has received intensive attention from researchers. However, a practical scenario of process fault diagnosis (i.e., multisource domain adaptation) has not been well solved under various working conditions. It is challenging since distribution difference coexists between different source domains and across source and target domains. In this study, a novel transfer learning model, feature-level and class-level based multi-source domain adaptation (FC-MSDA) is proposed for process fault diagnosis under varying working conditions. A common feature extractor is proposed to learn both global and local features from process signals. A feature selection module is developed to reduce negative transfer caused by irrelevant information in multiple source domains. Domain specific feature generator is developed for each source-target domain pair to learn domain-specific features. Moreover, class-level distribution alignment loss is proposed for each domain pair to settle the negative transfer caused by inconsistent label space between domains from different working conditions of process. An information fusion strategy is performed to ensemble multiple predictions. The experimental results on three industrial cases demonstrate the effectiveness of FC-MSDA in process fault diagnosis (i.e., FC-MSDA obtains the average accuracy of 99.17% on five transfer tasks in three phase process).

Globally Localized Multisource Domain Adaptation for Cross-Domain Fault Diagnosis With Category Shift.

Deep learning has demonstrated splendid performance in mechanical fault diagnosis on condition that source and target data are identically distributed. In engineering practice, however, the domain shift between source and target domains significantly limits the further application of intelligent algorithms. Despite various transfer techniques proposed, either they focus on single-source domain adaptation (SDA) or they utilize multisource domain globally or locally, which both cannot address the cross-domain diagnosis effectively, especially with category shift. To this end, we propose globally localized multisource DA for cross-domain fault diagnosis with category shift. Specifically, we construct a GlocalNet to fuse multisource information comprehensively, which consists of a feature generator and three classifiers. By optimizing the Wasserstein discrepancy of classifiers locally and accumulative higher order multisource moment globally, multisource DA is achieved from domain and class levels thus to reduce the shift on domain and category. To refine the classifier at sample level, a distilling strategy is presented. Finally, an adaptive weighting policy is employed for reliable result. To evaluate the effectiveness, the proposed method is compared with multiple methods on four bearing vibration datasets. Experimental results indicate the superiority and practicability of the proposed method for cross-domain fault diagnosis.

Multi-source domain adaptation with spatio-temporal feature extractor for EEG emotion recognition

Electroencephalogram (EEG) emotion recognition suffers from cross-domain identification difficulties mainly caused by cross-subject and cross-session differences. Inspired by domain adaptation, the study constructs a novel multi-source domain adaptation with a Spatio-temporal feature extractor (MSDA-SFE) for EEG emotion recognition, which could reduce the signal differences between subjects and between sessions to make the target domain features align with the source domain features easily. In common feature learning, a Spatiotemporal feature extraction module is constructed to acquire domain-invariant characteristics of the source and target domains in which one subject is selected randomly as the target domain, and the remaining subjects are source domains. Whereafter, the obtained target domain features are paired with other source domain features respectively to generate N-1 pairs of concatenated features. And then these features are translated into N-1 domain-specific EEG features through N-1 parallel branches, where the target domain features are better aligned in the latent space, and the classification boundary of target samples is obtained by minimizing the disparity between branches. Finally, domain-specific features are fed to respective classifiers to get N-1 predictions, and their mean is put as the final result. Extensive experiments are implemented on SEED, SEED-IV, and DEAP benchmark databases. And, results indicate that the MSDA-SFE network outperforms the other comparison methods. Besides, the additional experiment also illustrates that the method has a powerful generalization capacity.

Multi-Source Collaborative Contrastive Learning for Decentralized Domain Adaptation

Unsupervised multi-source domain adaptation aims to obtain a model working well on the unlabeled target domain by reducing the domain gap between the labeled source domains and the unlabeled target domain. Considering the data privacy and storage cost, data from multiple source domains and target domain are isolated and decentralized. This data decentralization scenario brings the difficulty of domain alignment for reducing the domain gap between the decentralized source domains and target domain, respectively. For conducting domain alignment under the data decentralization scenario, we propose Multi-source Collaborative Contrastive learning for decentralized Domain Adaptation (MCC-DA). The models from other domains are used as the bridge to reduce the domain gap. On the source domains and target domain, we penalize the inconsistency of data features extracted from the source domain models and target domain model by contrastive alignment. With the collaboration of source domain models and target domain model, the domain gap between decentralized source domains and target domain is reduced without accessing the data from other domains. The experiment results on multiple benchmarks indicate that our method can reduce the domain gap effectively and outperform the state-of-the-art methods significantly.

Unsupervised Adversarial Domain Adaptation Regression for Rate of Penetration Prediction

Summary The rate of penetration (ROP) refers to the speed at which a drill bit breaks through rock and deepens the drill hole. ROP is of great significance for drilling optimization and drilling cost savings. In real-world settings, the ROP data available for learning and training in a new oil field are scarce or even completely missing. In this paper, we propose a novel unsupervised multisource domain adaptation (MSDA) regression method for ROP that considers transferring the knowledge learned from a well-labelled source domain to the target domain with few labeled ROP data. First, we build a multisource unsupervised domain adaptation framework based on adversarial learning (WD-MUDA) which uses a weighted combination of multiple source domains to realize the fine-grained alignment of different data distributions. Specifically, we define a new similarity metric for different domains based on the Wasserstein distance. Furthermore, considering the uneven distribution of real drilling data samples, a novel regression loss is introduced to minimize the gradient discrepancy between multisource and target samples and improve the prediction accuracy of target samples. Extensive experiments on real drilling data sets reveal that the proposed method is effective and outperforms the state-of-the-art domain adaptation methods for ROP prediction.

Multisource Weighted Domain Adaptation With Evidential Reasoning for Activity Recognition

In recent years, wearable sensor-based human activity recognition (HAR) is becoming more and more attractive, especially in health monitoring and sports management. However, in order to obtain high-quality HAR, it is often necessary to get sufficient labeled activity data, which is very difficult, time-consuming and costly in a natural environment. To tackle this problem, multi-source domain adaptation is a promising method that aims to learn enough multi-source prior knowledge from labeled activity data, and then transfer this learned knowledge to the target unlabeled dataset. Thus, this paper presents a novel multi-source weighted domain adaptation with evidential reasoning (w-MSDAER) for HAR, which can effectively utilize complementary knowledge between multiple sources. Specifically, we first use the strategy of distribution alignment to learn local domain-invariant classifiers based on multi-source domains. And then, the reliabilities of these derived classifiers are comprehensively evaluated according to the belief function based the technique for order preference by similarity to ideal solution (BF-TOPSIS). Finally, the discounting fusion method is used to fuse the local classification results. Comprehensive experiments are conducted on two open-source datasets, and the results show that the proposed w-MSDAER significantly outperforms other state-of-art methods.

A two-stage domain alignment method for multi-source domain fault diagnosis

The issue of restricted target domain tags and constrained information offered by a single source domain in the intelligent fault diagnosis may be successfully resolved by multi-source domain adaptation. Compared with traditional domain adaptation methods, multisource domain adaptation methods face more difficult challenges: the differences between domains are more complex. Hence, a two-stage domain alignment method for multi-source domain fault diagnosis is proposed. The method is accomplished by developing a common feature extractor and several domain feature extractors and classifiers, along with the two-stage distribution adaptation method. Finally, the classifier is used to forecast target samples, while the voting mechanism is utilized to construct the target samples' pseudo labels. With the resulting pseudo labels, the final model training is completed.

Multi-representation symbolic convolutional neural network: a novel multisource cross-domain fault diagnosis method for rotating system

Multisource domain adaptation (MDA) methods have been preliminarily applied in cross-domain fault diagnosis of rotating system due to its correlation ability between different but related fields. However, it still remains challenging to learn domain-invariant representations under multisource scenarios. This article proposes a multi-representation symbolic convolutional neural network (MR-SCNN) for multisource cross-domain fault diagnosis of rotating system. The novelty of our work lies in three aspects. First, the proposed method combines symbolic dynamics with CNN to obtain a coarse-grained description of vibration signals, which could eliminate the negative transfer caused by subtle changes in dynamic characteristics among different source domains. Second, considering that most MDA methods ignore the significant limitations brought by statistical properties of the specific working condition, a multi-representation Softmax (MR-Softmax) is developed to learn domain-invariant discriminative representations by allowing the diversity of the predictions of samples with the same label. In addition, an undifferentiated adversarial training strategies is proposed to narrow the domain discrepancies and reasonably assess the residual negative transfer risk of different source domains. Based on the assessment, confidence coeffients are defined and embedded into MR-Softmax to extract and utilize the useful diagnostic knowledge on each source domain. Compared with several state-of-the-art diagnostic models, the experimental results confirm the validation of the proposed MR-SCNN method.

MASS: A Multisource Domain Adaptation Network for Cross-Subject Touch Gesture Recognition

Touch gesture recognition (TGR) plays a pivotal role in many applications, such as socially assistive robots and embodied telecommunication. However, one obstacle to practicality of existing TGR methods is the individual disparities across subjects. Moreover, a deep neural network trained with multiple existing subjects can easily lead to overfitting for a new subject. Hence, how to mitigate the discrepancies between the new and existing subjects and establish a generalized network for TGR is a significant task to realize reliable human–robot tactile interaction. In this article, a novel framework for Multisource domain Adaptation via Shared-Specific feature projection (MASS) is proposed, which incorporates intradomain discriminant, multidomain discriminant, and cross-domain consistency into a deep learning network for cross-subject TGR. Specifically, the MASS method first extracts the shared features in the common feature space of training subjects, with which a domain-general classifier is built. Then, the specific features of each pair of training and testing subjects are mapped and aligned in their common feature space, and multiple domain-specific classifiers are trained with the specific features. Finally, the domain-general classifier and domain-specific classifiers are ensembled to predict the label for the touch samples of a new subject. Experimental results performed on two datasets show that our proposed MASS method achieves remarkable results for cross-subject TGR. The code of MASS is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/AI-touch/MASS</uri> .

Intelligent fault diagnosis of rotating machinery using a multi-source domain adaptation network with adversarial discrepancy matching

Intelligent fault diagnosis of rotating machinery using a multi-source domain adaptation network with adversarial discrepancy matching