Domain-invariant Features Research Articles

A deep targeted transfer network with clustering pseudo-label learning for fault diagnosis across different Machines

In recent years, deep transfer models have addressed the issue of distribution shift between the source and target domains by learning domain-invariant features. However, in cross-machine fault diagnosis scenarios, existing deep learning models struggle to fit the conditional distribution of target domain samples, limiting the performance and generalization of domain adaptation models. To address these problems, we propose a deep targeted transfer network with clustering pseudo-label learning (DTTN-CPLL). DTTN-CPLL consists of three parts. First, a deep transfer network is constructed to extract cross-domain features. To reduce the intra-class distribution gap, a clustering pseudo-label learning algorithm is proposed to create subdomain labels within the target domain features. Then, we simultaneously minimize and maximize the entropy of features and the number of linearly independent vectors in the target domain to reduce the distance between subdomain features. Finally, under the constraint of local maximum mean discrepancy, we reduce the distribution discrepancy between the source and target domains at the subdomain feature level. We conducted 12 cross-machine transfer tasks on three open bearing datasets and a private high-speed train traction motor bearing dataset. The results demonstrate that, compared to other state-of-the-art models, DTTN-CPLL is effective and superior in cross-machine fault diagnosis.

Rolling bearing fault diagnosis based on the fusion of sparse filtering and discriminative domain adaptation method under multi-channel data-driven

Currently, the diagnostic performance of many deep learning algorithms may drop dramatically when the distribution of training data is significantly different from that of the test data. Moreover, the fault diagnosis approaches based on single-channel data may suffer problems such as large precision fluctuation, low reliability, and incomplete expression of fault features. To overcome the above deficiencies, a novel multi-channel data-driven fault recognition method based on the fusion of sparse filtering (SF) and discriminative domain adaptation (MSFDDA) is proposed in this article. Firstly, inspired by attention mechanisms and information fusion methods, a spectrum-based weighted multi-channel data fusion strategy is designed to fully utilize the data collected by sensors to obtain a more comprehensive representation of fault features. Then, the joint probability-based discriminative maximum mean discrepancy algorithm is introduced into the SF method to strengthen the capability of extracting the domain invariant features. Finally, two bearing datasets are employed to verify the validity of the MSFDDA method, which proved to be superior to other current domain adaptation methods.

Lightweight Knowledge Distillation-Based Transfer Learning Framework for Rolling Bearing Fault Diagnosis.

Compared to fault diagnosis across operating conditions, the differences in data distribution between devices are more pronounced and better aligned with practical application needs. However, current research on transfer learning inadequately addresses fault diagnosis issues across devices. To better balance the relationship between computational resources and diagnostic accuracy, a knowledge distillation-based lightweight transfer learning framework for rolling bearing diagnosis is proposed in this study. Specifically, a deep teacher-student model based on variable-scale residual networks is constructed to learn domain-invariant features relevant to fault classification within both the source and target domain data. Subsequently, a knowledge distillation framework incorporating a temperature factor is established to transfer fault features learned by the large teacher model in the source domain to the smaller student model, thereby reducing computational and parameter overhead. Finally, a multi-kernel domain adaptation method is employed to capture the feature probability distribution distance of fault characteristics between the source and target domains in Reproducing Kernel Hilbert Space (RKHS), and domain-invariant features are learned by minimizing the distribution distance between them. The effectiveness and applicability of the proposed method in situations of incomplete data across device types were validated through two engineering cases, spanning device models and transitioning from laboratory equipment to real-world operational devices.

Human-Robot handover task intention recognition framework by fusing human digital twin and deep domain adaptation

Industry 5.0 is conceived to achieve the expected high level of smart manufacturing and the more proactive and adaptive human-robot collaboration (HRC). In particular, human-robot handover tasks (HRHTs) are a notably crucial aspect of HRC, and resolving how to motivate robots to comprehend human handover intentions constitutes an exigent issue that demands resolution. To address these problems, A framework that integrates hierarchical human digital twin (HHDT) and deep domain adaptation is proposed, where HHDT model is built to digitise the human physical and physiological state and enhance the robot's perception of humans, a feature extractor-based on bidirectional long-short-term memory and spatio-temporal graph convolution network (BiLSTM-ST-GCN) is devised to extract latent spatio-temporal features of HRHTs intentions. Additionally, the framework incorporates a deep domain adaptation layer (DDAL) that facilitates knowledge transfer of HRHTs intentions by accounting for the distribution differences between the source and target operator objects. Extensive experiments demonstrate the superior performance of the proposed framework for HRHTs intention recognition and extraction of domain invariant features.

Curriculum learning-based domain generalization for cross-domain fault diagnosis with category shift

Intelligent fault diagnosis has witnessed significant advancements in the preceding years. Domain generalization-based methods can effectively alleviate the domain shift problem and be employ for fault diagnosis in unknown domains. Apart from the problem of domain shift, another challenge arises from the incomplete label space of each source domain due to the difficulty of data acquisition. Category shift can have a significant impact on the subsequent application of intelligent algorithms. To confront this more challenging and practical problem, we begin by formulating the setting of domain generalization with category shift. This paper proposes a Curriculum Learning-based Domain Generalization method (CLDG) to tackle with the intricate problem. The basic network consists of a feature extractor, a mixup-based reciprocal point learning classifier for tackling the category shift between the source and target domains, and a conditional domain discriminator for addressing the domain shift. In addition, we construct a curriculum learning strategy that uses the knowledge of categories with high observation degree to assist in extracting domain invariant features of lower ones, dealing with the category shift between the source domains and improving the generalization ability of the categorical information. Extensive experimental results on two datasets provide evidence for the effectiveness and superiority of the proposed algorithm in classifying known and missing classes in each source domain, as well as identifying unobserved failure modes in unknown target domains.

Interpretable Siamese dual attention enhancement transfer compound diagnostic model for unbalanced samples

The intelligent transfer diagnosis model is used to address the issue of feature drift caused by the changing working conditions of rotating parts in engineering. However, few models can perform transfer diagnosis on multiple unbalanced samples of rotating parts simultaneously, and even fewer models can visually enhance the domain-invariant features, making them more interpretable. To address these issues, we propose a novel interpretable Siamese dual attention enhancement transfer compound diagnosis model for unbalanced samples. The model can diagnose multiple rotating parts simultaneously and consists of a channel feature attention enhancement (CFAE) network, a fragment feature attention enhancement (FFAE) network, and a Siamese feature fusion (SFF) network. The CFAE network enhances features of different convolutional channels, the FFAE network improves segment features in various frequency domains, and the SFF network extracts domain-invariant features of diverse rotating components under varying working conditions. The model is validated using bearing fault data collected under different loads and planetary gear fault data obtained at varying speeds. Its diagnostic accuracy remains above 96.4%, and the diagnostic variance is controlled within 1.0%. The model has good interpretability for imbalanced sample domain-invariant features, providing an effective tool for interpretable transfer diagnosis in this compound engineering situation.

Unsupervised and Semi-Supervised Robust Spherical Space Domain Adaptation.

Adversarial domain adaptation has been an effective approach for learning domain-invariant features by adversarial training. In this paper, we propose a novel adversarial domain adaptation approach defined in the spherical feature space, in which we define spherical classifier for label prediction and spherical domain discriminator for discriminating domain labels. In the spherical feature space, we develop a spherical robust pseudo-label loss to utilize pseudo-labels robustly, which weights the importance of the estimated labels of target domain data by the posterior probability of correct labeling, modeled by the Gaussian-uniform mixture model in the spherical space. Our proposed approach can be generally applied to both unsupervised and semi-supervised domain adaptation settings. In particular, to tackle the semi-supervised domain adaptation setting where a few labeled target domain data are available for training, we propose a novel reweighted adversarial training strategy for effectively reducing the intra-domain discrepancy within the target domain. We also present theoretical analysis for the proposed method based on the domain adaptation theory. Extensive experiments are conducted on multiple benchmarks for object recognition, digit recognition, and face recognition. The results show that our method either surpasses or is competitive compared with the recent methods for both unsupervised and semi-supervised domain adaptation. Ablation studies also confirm the effectiveness of the spherical classifier, spherical discriminator, spherical robust pseudo-label loss, and reweighted adversarial training strategy.

Video Generalized Semantic Segmentation via Non-Salient Feature Reasoning and Consistency

Video semantic segmentation is beneficial for dynamic scene processing in real-world environments, and achieves superior performance on independent and identically distributed data. However, it suffers from performance degradation in environments with various domain styles, which is known as the distribution shift problem. Although some previous studies on image generalized semantic segmentation considered the distribution shift problem, temporal-frame information could not be used to obtain more accurate prediction. Thus, in this study, we explore a new task, known as the video generalized semantic segmentation (VGSS) task, which establishes a connection between continuous frames and domain generalization. We propose a novel method named Non-Salient Feature Reasoning and Consistency (NSFRC) for this task. Specifically, we first define the class-wise non-salient feature, which describes the features of the class-wise non-salient region that carry more generalized information. We then propose a class-wise non-salient feature reasoning strategy to select and enhance generalized channels adaptively. This strategy adopts a new form to use domain-invariant features by treating the domain-invariant features as prior information to assist domain-invariant model learning. Finally, we propose a non-salient centroid alignment loss to alleviate the temporally inconsistent and negative transfer problems in the VGSS task. We also extend our video-based framework to the image generalized semantic segmentation (IGSS) task. Experiments demonstrate that our NSFRC framework yields significant improvements in both the VGSS and IGSS tasks. To explain the idea of this research in a clear and attractive way, we provide the visual abstract shown in Fig. 1.

Privacy-Preserving Breast Cancer Classification: A Federated Transfer Learning Approach.

Breast cancer is deadly cancer causing a considerable number of fatalities among women in worldwide. To enhance patient outcomes as well as survival rates, early and accurate detection is crucial. Machine learning techniques, particularly deep learning, have demonstrated impressive success in various image recognition tasks, including breast cancer classification. However, the reliance on large labeled datasets poses challenges in the medical domain due to privacy issues and data silos. This study proposes a novel transfer learning approach integrated into a federated learning framework to solve the limitations of limited labeled data and data privacy in collaborative healthcare settings. For breast cancer classification, the mammography and MRO images were gathered from three different medical centers. Federated learning, an emerging privacy-preserving paradigm, empowers multiple medical institutions to jointly train the global model while maintaining data decentralization. Our proposed methodology capitalizes on the power of pre-trained ResNet, a deep neural network architecture, as a feature extractor. By fine-tuning the higher layers of ResNet using breast cancer datasets from diverse medical centers, we enable the model to learn specialized features relevant to different domains while leveraging the comprehensive image representations acquired from large-scale datasets like ImageNet. To overcome domain shift challenges caused by variations in data distributions across medical centers, we introduce domain adversarial training. The model learns to minimize the domain discrepancy while maximizing classification accuracy, facilitating the acquisition of domain-invariant features. We conducted extensive experiments on diverse breast cancer datasets obtained from multiple medical centers. Comparative analysis was performed to evaluate the proposed approach against traditional standalone training and federated learning without domain adaptation. When compared with traditional models, our proposed model showed a classification accuracy of 98.8% and a computational time of 12.22s. The results showcase promising enhancements in classification accuracy and model generalization, underscoring the potential of our method in improving breast cancer classification performance while upholding data privacy in a federated healthcare environment.

Style-Guided Adversarial Teacher for Cross-Domain Object Detection

The teacher–student framework is widely employed for cross-domain object detection. However, it suffers from two problems. One is that large distribution discrepancies will cause critical performance drops. The other is that the samples that deviate from the overall distributions of both domains will greatly mislead the model. To solve these problems, we propose a style-guided adversarial teacher (SGAT) method for domain adaptation. Specifically, on the domain level, we generate target-like images based on source images to effectively narrow the gaps between domains. On the sample level, we denoise samples by estimating the probability density ratio of the ‘target-style’ and target distributions, which could filter out the unrelated samples and highlight the related ones. In this way, we could guarantee reliable samples. With these reliable samples, we learn the domain-invariant features through teacher–student mutual learning and adversarial learning. Extensive experiments verify the effectiveness of our method. In particular, we achieve 52.9% mAP on Clipart1k and 42.7% on Comic2k, which are 6.4% and 5.0% higher than the compared baselines.

Learning to Generalize over Subpartitions for Heterogeneity-Aware Domain Adaptive Nuclei Segmentation

Annotation scarcity and cross-modality/stain data distribution shifts are two major obstacles hindering the application of deep learning models for nuclei analysis, which holds a broad spectrum of potential applications in digital pathology. Recently, unsupervised domain adaptation (UDA) methods have been proposed to mitigate the distributional gap between different imaging modalities for unsupervised nuclei segmentation in histopathology images. However, existing UDA methods are built upon the assumption that data distributions within each domain should be uniform. Based on the over-simplified supposition, they propose to align the histopathology target domain with the source domain integrally, neglecting severe intra-domain discrepancy over subpartitions incurred by mixed cancer types and sampling organs. In this paper, for the first time, we propose to explicitly consider the heterogeneity within the histopathology domain and introduce open compound domain adaptation (OCDA) to resolve the crux. In specific, a two-stage disentanglement framework is proposed to acquire domain-invariant feature representations at both image and instance levels. The holistic design addresses the limitations of existing OCDA approaches which struggle to capture instance-wise variations. Two regularization strategies are specifically devised herein to leverage the rich subpartition-specific characteristics in histopathology images and facilitate subdomain decomposition. Moreover, we propose a dual-branch nucleus shape and structure preserving module to prevent nucleus over-generation and deformation in the synthesized images. Experimental results on both cross-modality and cross-stain scenarios over a broad range of diverse datasets demonstrate the superiority of our method compared with state-of-the-art UDA and OCDA methods.Graphical abstract

A multi-source subdomain adaptation fault diagnosis method based on unidirectional movement of the target domain

The traditional domain adaptation method for fault diagnosis of axial fans faces two main problems: (1) source domain moves to target domain makes the source feature distribution changed; (2) the narrow decision boundary of source domain features leads to misclassification of target samples. Therefore, a multi-source subdomain adaption fault diagnosis method based on unidirectional movement of the target domain is proposed. The method uses triplet-center loss to improve the discrimination of target domain samples, which reducing intra-class distance and increasing inter-class distance of source domain features; extracting the domain invariant feature of the target samples by asymmetric adversarial and improved subdomain feature distance measurement; the cosine similarity is used to align the classifiers’ outputs of different source domains; the mean value of all classifiers’ outputs are used as pseudo labels, and the pseudo labels are optimized by maximum entropy to improve their reliability. A large number of experiments show that this method has a significant effect on solving the problem of cross conditions fault diagnosis.

Correlation enhanced distribution adaptation for prediction of fall risk

With technological advancements in diagnostic imaging, smart sensing, and wearables, a multitude of heterogeneous sources or modalities are available to proactively monitor the health of the elderly. Due to the increasing risks of falls among older adults, an early diagnosis tool is crucial to prevent future falls. However, during the early stage of diagnosis, there is often limited or no labeled data (expert-confirmed diagnostic information) available in the target domain (new cohort) to determine the proper treatment for older adults. Instead, there are multiple related but non-identical domain data with labels from the existing cohort or different institutions. Integrating different data sources with labeled and unlabeled samples to predict a patient's condition poses a significant challenge. Traditional machine learning models assume that data for new patients follow a similar distribution. If the data does not satisfy this assumption, the trained models do not achieve the expected accuracy, leading to potential misdiagnosing risks. To address this issue, we utilize domain adaptation (DA) techniques, which employ labeled data from one or more related source domains. These DA techniques promise to tackle discrepancies in multiple data sources and achieve a robust diagnosis for new patients. In our research, we have developed an unsupervised DA model to align two domains by creating a domain-invariant feature representation. Subsequently, we have built a robust fall-risk prediction model based on these new feature representations. The results from simulation studies and real-world applications demonstrate that our proposed approach outperforms existing models.

AdvMix: Adversarial Mixing Strategy for Unsupervised Domain Adaptive Object Detection

Recent object detection networks suffer from performance degradation when training data and test data are distinct in image styles and content distributions. In this paper, we propose a domain adaptive method, Adversarial Mixing (AdvMix), where the label-rich source domain and unlabeled target domain are jointly trained by the adversarial feature alignment and a self-training strategy. To diminish the style gap, we design the Adversarial Gradient Reversal Layer (AdvGRL), containing a global-level domain discriminator to align the domain features by gradient reversal, and an adversarial weight mapping function to enhance the stability of domain-invariant features by hard example mining. To eliminate the content gap, we introduce a region mixing self-supervised training strategy where a region of the target image with the highest confidence is selected to merge with the source image, and the synthesis image is self-supervised by the consistency loss. To improve the reliability of self-training, we propose a strict confidence metric combining both object and bounding box uncertainty. Extensive experiments conducted on three benchmarks demonstrate that AdvMix achieves prominent performance in terms of detection accuracy, surpassing existing domain adaptive methods by nearly 5% mAP.

ST-GAN: A Swin Transformer-Based Generative Adversarial Network for Unsupervised Domain Adaptation of Cross-Modality Cardiac Segmentation.

Unsupervised domain adaptation (UDA) methods have shown great potential in cross-modality medical image segmentation tasks, where target domain labels are unavailable. However, the domain shift among different image modalities remains challenging, because the conventional UDA methods are based on convolutional neural networks (CNNs), which tend to focus on the texture of images and cannot establish the global semantic relevance of features due to the locality of CNNs. This paper proposes a novel end-to-end Swin Transformer-based generative adversarial network (ST-GAN) for cross-modality cardiac segmentation. In the generator of ST-GAN, we utilize the local receptive fields of CNNs to capture spatial information and introduce the Swin Transformer to extract global semantic information, which enables the generator to better extract the domain-invariant features in UDA tasks. In addition, we design a multi-scale feature fuser to sufficiently fuse the features acquired at different stages and improve the robustness of the UDA network. We extensively evaluated our method with two cross-modality cardiac segmentation tasks on the MS-CMR 2019 dataset and the M&Ms dataset. The results of two different tasks show the validity of ST-GAN compared with the state-of-the-art cross-modality cardiac image segmentation methods.

Multi-source domain adaptation based tempo-spatial convolution network for cross-subject EEG classification in RSVP task

Objective. Many subject-dependent methods were proposed for electroencephalogram (EEG) classification in rapid serial visual presentation (RSVP) task, which required a large amount of data from new subject and were time-consuming to calibrate system. Cross-subject classification can realize calibration reduction or zero calibration. However, cross-subject classification in RSVP task is still a challenge. Approach. This study proposed a multi-source domain adaptation based tempo-spatial convolution (MDA-TSC) network for cross-subject RSVP classification. The proposed network consisted of three modules. First, the common feature extraction with multi-scale tempo-spatial convolution was constructed to extract domain-invariant features across all subjects, which could improve generalization of the network. Second, the multi-branch domain-specific feature extraction and alignment was conducted to extract and align domain-specific feature distributions of source and target domains in pairs, which could consider feature distribution differences among source domains. Third, the domain-specific classifier was exploited to optimize the network through loss functions and obtain prediction for the target domain. Main results. The proposed network was evaluated on the benchmark RSVP dataset, and the cross-subject classification results showed that the proposed MDA-TSC network outperformed the reference methods. Moreover, the effectiveness of the MDA-TSC network was verified through both ablation studies and visualization. Significance. The proposed network could effectively improve cross-subject classification performance in RSVP task, and was helpful to reduce system calibration time.

Enhanced residual convolutional domain adaptation network with CBAM for RUL prediction of cross-machine rolling bearing

Remaining useful life (RUL) prediction of rolling bearing is one of the important measures to ensure the reliable operation of mechanical equipment. Most of the existing methods are domain adaptation (DA) based RUL prediction on the same machine with different conditions, but few on cross-machine. DA can cope with the data distribution discrepancy (domain shift) under different machines or other conditions, but the potential negative transfer will affect the effect of DA and prediction performance. Therefore, an enhanced residual convolutional domain adaptation network (ERCDAN) is designed for cross-machine rolling bearing RUL prediction. Firstly, the enhanced residual convolutional module (ERCM) is designed for degradation feature extraction from limited data, and with the convolutional block attention module (CBAM) to enhance the extracted features. Secondly, the DA module with a collaborative full connection structure and attenuation multi-kernel maximum mean discrepancy is designed for mitigating negative transfer to effective domain-invariant feature extraction. Finally, the experimental analysis of cross-machine rolling bearing RUL prediction is conducted on the PHM2012, XJTU-SY, and EBFL datasets. The results show that the proposed method can not only effectively achieve cross-machine RUL prediction, but also has good cross-bearing prediction performance with different conditions on the same machine, reflecting good generalization performance.

Wavelet packet decomposition with motif patterns for rolling bearing fault diagnosis under variable working loads

Bearing intelligent diagnosis based on signal processing has been a hot research topic. However, due to the different data distribution caused by the variable working loads, the model learned from source domain has poor performance in target domain. To solve this problem, a feature extraction method named Wavelet Packet Decomposition with Motif Patterns (WPDMP) is proposed. Firstly, multiscale signals are obtained using wavelet packet decomposition; then, the MP features of these multiscale signals and the original signal are extracted; finally, these MPs are combined as input vector of support vector classification (SVC) for fault identification. Compared with other methods, the proposed method has extraordinary superiority for unlabeled target domain fault diagnosis. In addition, the feature visualization results show that the proposed model can extract domain invariant features, so the proposed model has considerable research prospects.

Cross-domain Recommendation via Dual Adversarial Adaptation

Data scarcity is a perpetual challenge of recommendation systems, and researchers have proposed a variety of cross-domain recommendation methods to alleviate the problem of data scarcity in target domains. However, in many real-world cross-domain recommendation systems, the source domain and the target domain are sampled from different data distributions, which obstructs the cross-domain knowledge transfer. In this article, we propose to specifically align the data distributions between the source domain and the target domain to alleviate imbalanced sample distribution and thus challenge the data scarcity issue in the target domain. Technically, our proposed approach builds a dual adversarial adaptation (DAA) framework to adversarially train the target model together with a pre-trained source model. Two domain discriminators play the two-player minmax game with the target model and guide the target model to learn reliable domain-invariant features that can be transferred across domains. At the same time, the target model is calibrated to learn domain-specific information of the target domain. In addition, we formulate our approach as a plug-and-play module to boost existing recommendation systems. We apply the proposed method to address the issues of insufficient data and imbalanced sample distribution in real-world Click-through Rate/Conversion Rate predictions on two large-scale industrial datasets. We evaluate the proposed method in scenarios with and without overlapping users/items, and extensive experiments verify that the proposed method is able to significantly improve the prediction performance on the target domain. For instance, our method can boost PLE with a performance improvement of 15.4% in terms of Area Under Curve compared with single-domain PLE on our private game dataset. In addition, our method is able to surpass single-domain MMoE by 6.85% on the public datasets. Code: https://github.com/TL-UESTC/DAA .

Exploring Structure Incentive Domain Adversarial Learning for Generalizable Sleep Stage Classification

Sleep stage classification is crucial for sleep state monitoring and health interventions. In accordance with the standards prescribed by the American Academy of Sleep Medicine, a sleep episode follows a specific structure comprising five distinctive sleep stages that collectively form a sleep cycle. Typically, this cycle repeats about five times, providing an insightful portrayal of the subject’s physiological attributes. The progress of deep learning and advanced domain generalization methods allows automatic and even adaptive sleep stage classification. However, applying models trained with visible subject data to invisible subject data remains challenging due to significant individual differences among subjects. Motivated by the periodic category-complete structure of sleep stage classification, we propose a Structure Incentive Domain Adversarial learning (SIDA) method that combines the sleep stage classification method with domain generalization to enable cross-subject sleep stage classification. SIDA includes individual domain discriminators for each sleep stage category to decouple subject dependence differences among different categories and fine-grained learning of domain-invariant features. Furthermore, SIDA directly connects the label classifier and domain discriminators to promote the training process. Experiments on three benchmark sleep stage classification datasets demonstrate that the proposed SIDA method outperforms other state-of-the-art sleep stage classification and domain generalization methods and achieves the best cross-subject sleep stage classification results.