Domain Shift Problem Research Articles

Graph-Based Domain Adaptation Few-Shot Learning for Hyperspectral Image Classification

Due to a lack of labeled samples, deep learning methods generally tend to have poor classification performance in practical applications. Few-shot learning (FSL), as an emerging learning paradigm, has been widely utilized in hyperspectral image (HSI) classification with limited labeled samples. However, the existing FSL methods generally ignore the domain shift problem in cross-domain scenes and rarely explore the associations between samples in the source and target domain. To tackle the above issues, a graph-based domain adaptation FSL (GDAFSL) method is proposed for HSI classification with limited training samples, which utilizes the graph method to guide the domain adaptation learning process in a uniformed framework. First, a novel deep residual hybrid attention network (DRHAN) is designed to extract discriminative embedded features efficiently for few-shot HSI classification. Then, a graph-based domain adaptation network (GDAN), which combines graph construction with domain adversarial strategy, is proposed to fully explore the domain correlation between source and target embedded features. By utilizing the fully explored domain correlations to guide the domain adaptation process, a domain invariant feature metric space is learned for few-shot HSI classification. Comprehensive experimental results conducted on three public HSI datasets demonstrate that GDAFSL is superior to the state-of-the-art with a small sample size.

Improving pseudo labels with intra-class similarity for unsupervised domain adaptation

Unsupervised domain adaptation (UDA) transfers knowledge from a label-rich source domain to a different but related fully-unlabeled target domain. To address the problem of domain shift, more and more UDA methods adopt pseudo labels of the target samples to improve the generalization ability on the target domain. However, inaccurate pseudo labels of the target samples may yield suboptimal performance with error accumulation during the optimization process. Moreover, once the pseudo labels are generated, how to remedy the generated pseudo labels is far from explored. In this paper, we propose a novel approach to improve the accuracy of the pseudo labels in the target domain. It first generates coarse pseudo labels by a conventional UDA method. Then, it iteratively exploits the intra-class similarity of the target samples for improving the generated coarse pseudo labels, and aligns the source and target domains with the improved pseudo labels. The accuracy improvement of the pseudo labels is made by first deleting dissimilar samples, and then using spanning trees to eliminate the samples with the wrong pseudo labels in the intra-class samples. We have applied the proposed approach to several conventional UDA methods as an additional term. Experimental results demonstrate that the proposed method can boost the accuracy of the pseudo labels and further lead to more discriminative and domain invariant features than the conventional baselines.

ADAST: Attentive Cross-Domain EEG-Based Sleep Staging Framework With Iterative Self-Training

Sleep staging is of great importance in the diagnosis and treatment of sleep disorders. Recently, numerous data-driven deep learning models have been proposed for automatic sleep staging. They mainly train the model on a large public labeled sleep dataset and test it on a smaller one with subjects of interest. However, they usually assume that the train and test data are drawn from the same distribution, which may not hold in real-world scenarios. Unsupervised domain adaption (UDA) has been recently developed to handle this domain shift problem. However, previous UDA methods applied for sleep staging have two main limitations. First, they rely on a totally shared model for the domain alignment, which may lose the domain-specific information during feature extraction. Second, they only align the source and target distributions globally without considering the class information in the target domain, which hinders the classification performance of the model while testing. In this work, we propose a novel adversarial learning framework called ADAST to tackle the domain shift problem in the unlabeled target domain. First, we develop an unshared attention mechanism to preserve the domain-specific features in both domains. Second, we design an iterative self-training strategy to improve the classification performance on the target domain via target domain pseudo labels. We also propose dual distinct classifiers to increase the robustness and quality of the pseudo labels. The experimental results on six cross-domain scenarios validate the efficacy of our proposed framework and its advantage over state-of-the-art UDA methods.

Prototype-guided multi-scale domain adaptation for Alzheimer's disease detection

Alzheimer's disease (AD) is the most common form of dementia and there is no effective treatment currently. Using artificial intelligence technology to assist the diagnosis and intervention as early as possible is of great significance to delay the development of AD. Structural Magnetic Resonance Imaging (sMRI) has shown great practical values on computer-aided AD diagnosis. Affected by data from different sources or acquisition domains in realistic scenarios, MRI data often suffer from domain shift problem. In this paper, we propose a deep Prototype-Guided Multi-Scale Domain Adaptation (PMDA) framework to handle MRI data with domain shift problem, and realize automatic auxiliary diagnosis of AD, Mild Cognitive Impairment (MCI) and Cognitively Normal (CN). PMDA is composed of three modules: (1) MRI multi-scale feature extraction module combines the advantages of 3D convolution and self-attention to effectively extract multi-scale features in high-dimensional space, (2) Prototype Maximum Density Divergence (Pro-MDD) module adopts prototype learning to constrain the feature outlier samples in a mini-batch when MDD is used to align source domain and target domain, and (3) Adversarial Domain Adaptation module is applied to achieve global feature alignment of the source domain and target domain and co-training two distinctive discriminators to mitigate the over-fitting issue. Experiments have been performed on 3T and 1.5T sMRI with domain shift in ADNI dataset. The experimental results demonstrated that the proposed framework PMDA outperforms supervised learning methods and several state-of-the-art domain adaptation methods and achieves a superior accuracy of 92.11%, 76.01% and 82.37% on AD vs. CN, AD vs. MCI, and MCI vs. CN tasks, respectively.

Task-aware asynchronous multi-task model with class incremental contrastive learning for surgical scene understanding.

Surgery scene understanding with tool-tissue interaction recognition and automatic report generation can play an important role in intra-operative guidance, decision-making and postoperative analysis in robotic surgery. However, domain shifts between different surgeries with inter and intra-patient variation and novel instruments' appearance degrade the performance of model prediction. Moreover, it requires output from multiple models, which can be computationally expensive and affect real-time performance. A multi-task learning (MTL) model is proposed for surgical report generation and tool-tissue interaction prediction that deals with domain shift problems. The model forms of shared feature extractor, mesh-transformer branch for captioning and graph attention branch for tool-tissue interaction prediction. The shared feature extractor employs class incremental contrastive learning to tackle intensity shift and novel class appearance in the target domain. We design Laplacian of Gaussian-based curriculum learning into both shared and task-specific branches to enhance model learning. We incorporate a task-aware asynchronous MTL optimization technique to fine-tune the shared weights and converge both tasks optimally. The proposed MTL model trained using task-aware optimization and fine-tuning techniques reported a balanced performance (BLEU score of 0.4049 for scene captioning and accuracy of 0.3508 for interaction detection) for both tasks on the target domain and performed on-par with single-task models in domain adaptation. The proposed multi-task model was able to adapt to domain shifts, incorporate novel instruments in the target domain, and perform tool-tissue interaction detection and report generation on par with single-task models.

Multi-Scale Feature Map Aggregation and Supervised Domain Adaptation of Fully Convolutional Networks for Urban Building Footprint Extraction

Automated building footprint extraction requires the Deep Learning (DL)-based semantic segmentation of high-resolution Earth observation images. Fully convolutional networks (FCNs) such as U-Net and ResUNET are widely used for such segmentation. The evolving FCNs suffer from the inadequate use of multi-scale feature maps in their backbone of convolutional neural networks (CNNs). Furthermore, the DL methods are not robust in cross-domain settings due to domain-shift problems. Two scale-robust novel networks, namely MSA-UNET and MSA-ResUNET, are developed in this study by aggregating the multi-scale feature maps in U-Net and ResUNET with partial concepts of the feature pyramid network (FPN). Furthermore, supervised domain adaptation is investigated to minimise the effects of domain-shift between the two datasets. The datasets include the benchmark WHU Building dataset and a developed dataset with 5× fewer samples, 4× lower spatial resolution and complex high-rise buildings and skyscrapers. The newly developed networks are compared to six state-of-the-art FCNs using five metrics: pixel accuracy, adjusted accuracy, F1 score, intersection over union (IoU), and the Matthews Correlation Coefficient (MCC). The proposed networks outperform the FCNs in the majority of the accuracy measures in both datasets. Compared to the larger dataset, the network trained on the smaller one shows significantly higher robustness in terms of adjusted accuracy (by 18%), F1 score (by 31%), IoU (by 27%), and MCC (by 29%) during the cross-domain validation of MSA-UNET. MSA-ResUNET shows similar improvements, concluding that the proposed networks when trained using domain adaptation increase the robustness and minimise the domain-shift between the datasets of different complexity.

ShipGAN: Generative Adversarial Network based simulation-to-real image translation for ships

Recent advances in robotics and autonomous systems (RAS) have significantly improved the autonomy level of unmanned surface vehicles (USVs) and made them capable of undertaking demanding tasks in various environments. During the operation of USVs, apart from normal situations, it is those unexpected scenes, such as busy waterways or navigation in dust/nighttime, impose most dangers to USVs as these scenes are rarely seen during training. Such a rare occurrence also makes the manual collection and recording of these scenes into dataset difficult, expensive and inefficient, with the majority of existing public available datasets not able to fully cover them. One of many plausible solutions is to purposely generate these data using computer vision techniques with the assistance from high-fidelity simulations that can create various desirable motions/scenarios. However, the stylistic difference between the simulation images and the natural images would cause a domain shift problem. Hence, there is a need for designing a method that can transfer the data distribution and styles of the simulation images into the realistic domain. This paper proposes and evaluates a novel solution to fill this gap using a Generative Adversarial Network (GAN) based model, ShipGAN, to translate the simulation images into realistic images. Experiments were carried out to investigate the feasibility of generating realistic images using GAN-based image translation models. The synthetic realistic images from the simulation images were demonstrated to be reliable by the object detection and image segmentation algorithms trained with natural images.

Progressive cross-domain knowledge distillation for efficient unsupervised domain adaptive object detection

Unsupervised domain adaptation (UDA) is a technique for relieving domain shifts via transferring relevant domain knowledge from the full-labeled source domain to an unlabeled target domain. While tremendous advances have been witnessed recently, the adoption of deep CNN-based UDA methods in real-world scenarios is still constrained by low-resource computers. Most prior strategies either handle domain shift problems via UDA or compress CNNs using knowledge distillation (KD), we seek to implement the model on constrained-resource devices to learn domain adaptive knowledge without sacrificing accuracy. In this paper, we proposed a three-step Progressive Cross-domain Knowledge Distillation (PCdKD) paradigm for efficient unsupervised adaptive object detection, since directly alleviating the significant discrepancy across domains could result in unstable training procedures and suboptimal performance. First, we apply pixel-level alignment via image-to-image translation to reduce the appearance discrepancy between different domains. Then, a focal multi-domain discriminator is utilized to train the teacher–student peer networks for gradually distilling domain adaptive knowledge in a cooperative manner. Finally, reliable pseudo labels obtained by the adapted teacher detector are further utilized to retrain the teacher–student models. Our proposed method can boost the transferability of the teacher model as well as enhance the student model to meet the demand of real-time applications. Comprehensive experiments on four different cross-domain datasets show that our PCdKD outperforms most existing state-of-the-art approaches.

Self-supervised Learning for Label-Efficient Sleep Stage Classification: A Comprehensive Evaluation.

The past few years have witnessed a remarkable advance in deep learning for EEG-based sleep stage classification (SSC). However, the success of these models is attributed to possessing a massive amount of labeled data for training, limiting their applicability in real-world scenarios. In such scenarios, sleep labs can generate a massive amount of data, but labeling can be expensive and time-consuming. Recently, the self-supervised learning (SSL) paradigm has emerged as one of the most successful techniques to overcome labels' scarcity. In this paper, we evaluate the efficacy of SSL to boost the performance of existing SSC models in the few-labels regime. We conduct a thorough study on three SSC datasets, and we find that fine-tuning the pretrained SSC models with only 5% of labeled data can achieve competitive performance to the supervised training with full labels. Moreover, self-supervised pretraining helps SSC models to be more robust to data imbalance and domain shift problems.

LVQ Treatment for Zero-Shot Learning

In image classification, there are no labeled training instances for some classes, which are therefore called unseen classes or test classes. To classify these classes, zero-shot learning (ZSL) was developed, which typically attempts to learn a mapping from the (visual) feature space to the semantic space in which the classes are represented by a list of semantically meaningful attributes. However, the fact that this mapping is learned without using instances of the test classes affects the performance of ZSL, which is known as the domain shift problem. In this study, we propose to apply the learning vector quantization (LVQ) algorithm in the semantic space once the mapping is determined. First and foremost, this allows us to refine the prototypes of the test classes with respect to the learned mapping, which reduces the effects of the domain shift problem. Secondly, the LVQ algorithm increases the margin of the 1-NN classifier used in ZSL, resulting in better classification. Moreover, for this work, we consider a range of LVQ algorithms, from initial to advanced variants, and applied them to a number of state-of-the-art ZSL methods, then obtained their LVQ extensions. The experiments based on five ZSL benchmark datasets showed that the LVQ-empowered extensions of the ZSL methods are superior to their original counterparts in almost all settings.

Drop to Transfer: Learning Transferable Features for Robot Tactile Material Recognition in Open Scene

Tactile feedback is an important way for robots to perceive the environment. In the open scenes, many uncertain factors lead to the change of the external environment, such as the re-installation of the robot end-effector and the change of exploratory motions. This situation unavoidably raises the domain shift problem, which makes it difficult for the robot to fit the new open environment if it makes decisions only based on the knowledge extracted from the closed environment. Thus, we propose a new deep unsupervised domain adaptive material recognition model, called Drop To Transfer (DTT), which adaptively learns tactile transferable features to achieve accurate material recognition in open scenes. DTT performs the clustering hypothesis on the target domain samples using the adversarial dropout. And in each training iteration, high-gradient features are progressively removed to enhance the expression of other transferable features. Meanwhile, the Maximum Mean Discrepancy (MMD) metric is added in the optimization process to achieve feature alignment between the source and target domain distributions. In addition, we design an adaptive weighted optimization strategy to optimize each loss in DTT effectively. Experimental results show that the proposed method can effectively learn the transferable features and reduce the domain shift problem for the robot tactile perception task in the open scenes.

Unsupervised Domain Adaptation Augmented by Mutually Boosted Attention for Semantic Segmentation of VHR Remote Sensing Images

This work investigates unsupervised domain adaptation (UDA)-based semantic segmentation of very high-resolution (VHR) remote sensing (RS) images from different domains. Most existing UDA methods resort to generative adversarial networks (GANs) to cope with the domain shift problem caused by the discrepancies across different domains. However, these GAN-based UDA methods directly align two domains in the appearance, latent, or output space based on convolutional neural networks (CNNs), making them ineffective in exploiting long-range dependencies across the high-level feature maps derived from different domains. Unfortunately, such high-level features play an essential role in characterizing RS images with complex content. To circumvent this obstacle, a mutually boosted attention transformer (MBATrans) is proposed to capture cross-domain dependencies of semantic feature representations in this work. Compared with conventional UDA methods, MBATrans can significantly reduce domain discrepancies by capturing transferable features using global attention. More specifically, MBATrans utilizes a novel mutually boosted attention (MBA) module to align cross-domain feature maps while enhancing domain-general features. Furthermore, a novel GAN-based network with improved discriminative capability is devised by integrating an additional discriminator to learn domain-specific features. Extensive experiments on two large-scale VHR RS datasets, namely, International Society for Photogrammetry and Remote Sensing (ISPRS) Potsdam and Vaihingen, confirm the superior performance of the proposed MBATrans-augmented GAN (MBATA-GAN) architecture. The source code in this work is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/sstary/SSRS</uri> .

DOC: Text Recognition via Dual Adaptation and Clustering

More recently, unsupervised domain adaptation has been introduced to text image recognition tasks for serious domain shift problem, which can transfer knowledge from source domains to target ones. Moreover, in unsupervised domain adaptation for text recognition, there is no label information in the target domain to supervise the domain adaptation, especially at the character. Several existing methods regard a text image as a whole and perform only on global feature adaptation, neglecting local-level feature adaptation, i.e., characters. Others methods only focus their attention on word-level feature alignment while ignoring the categories of local-level characters. To address these issues, we propose a text recognition model via Dual adaptatiOn and Clustering, DOC for short. Regarding word-level, we construct a Global Discriminator for global feature adaptation to reduce text layout bias between source and target domains. Regarding character-level, we propose an Adaptive Feature Clustering (AFC) module, which can extract invariant character features through a local-level discriminator for adaptation. Moreover, it enhances the local-feature adaptation by a clustering scheme, which evaluates the feature adaptation by leveraging the knowledge from the source domain as much as possible. In this way, it can pay more attention to the differences in fine-grained characters. Extensive experiments on benchmark datasets demonstrate that our framework can achieve state-of-the-art performance. We have released the code. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>

Hierarchical Style-Aware Domain Generalization for Remote Physiological Measurement.

The utilization of remote photoplethysmography (rPPG) technology has gained attention in recent years due to its ability to extract blood volume pulse (BVP) from facial videos, making it accessible for various applications such as health monitoring and emotional analysis. However, the BVP signal is susceptible to complex environmental changes or individual differences, causing existing methods to struggle in generalizing for unseen domains. This article addresses the domain shift problem in rPPG measurement and shows that most domain generalization methods fail to work well in this problem due to ambiguous instance-specific differences. To address this, the article proposes a novel approach called Hierarchical Style-aware Representation Disentangling (HSRD). HSRD improves generalization capacity by separating domain-invariant and instance-specific feature space during training, which increases the robustness of out-of-distribution samples during inference. This work presents state-of-the-art performance against several methods in both cross and intra-dataset settings.

Generative Neural Network-Based Online Domain Adaptation (GNN-ODA) Approach for Incomplete Target Domain Data

Recently, monitoring machine health with artificial intelligence (AI) models becomes more efficient using either vibration or audio signals. However, the vibration signals of machines with different tool materials or under different operating conditions are not consistent. Hence, the transfer learning algorithm used in this study is presented for domain adaptation to improve the inference accuracy. Herein, we introduce a domain adaptation technique to solve domain shift problems during machine health monitoring. Additionally, most existing articles assumed to have obtained a complete target data. However, these data are continuously acquired; that is, the target data are incomplete during the monitoring phase. Thus, a generative neural network-based online domain adaptation model (GNN-ODA) is proposed. This will improve the test accuracy by generating complete target data and further train the classifier using the complete source data. The experiments indicate that the proposed method outperforms other domain adaptation methods wherein target data were incomplete. The average accuracy on both the tool wear and bearing datasets exceeded 90% when the source and target domains were under similar operating conditions.

Contrastive Semi-Supervised Learning for Domain Adaptive Segmentation Across Similar Anatomical Structures.

Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance for medical image segmentation, yet need plenty of manual annotations for training. Semi-Supervised Learning (SSL) methods are promising to reduce the requirement of annotations, but their performance is still limited when the dataset size and the number of annotated images are small. Leveraging existing annotated datasets with similar anatomical structures to assist training has a potential for improving the model's performance. However, it is further challenged by the cross-anatomy domain shift due to the image modalities and even different organs in the target domain. To solve this problem, we propose Contrastive Semi-supervised learning for Cross Anatomy Domain Adaptation (CS-CADA) that adapts a model to segment similar structures in a target domain, which requires only limited annotations in the target domain by leveraging a set of existing annotated images of similar structures in a source domain. We use Domain-Specific Batch Normalization (DSBN) to individually normalize feature maps for the two anatomical domains, and propose a cross-domain contrastive learning strategy to encourage extracting domain invariant features. They are integrated into a Self-Ensembling Mean-Teacher (SE-MT) framework to exploit unlabeled target domain images with a prediction consistency constraint. Extensive experiments show that our CS-CADA is able to solve the challenging cross-anatomy domain shift problem, achieving accurate segmentation of coronary arteries in X-ray images with the help of retinal vessel images and cardiac MR images with the help of fundus images, respectively, given only a small number of annotations in the target domain. Our code is available at https://github.com/HiLab-git/DAG4MIA.

Integrated Multiscale Domain Adaptive YOLO.

The area of domain adaptation has been instrumental in addressing the domain shift problem encountered by many deep learning applications. This problem arises due to the difference between the distributions of source data used for training in comparison with target data used during realistic testing scenarios. In this paper, we introduce a novel MultiScale Domain Adaptive YOLO (MS-DAYOLO) framework that employs multiple domain adaptation paths and corresponding domain classifiers at different scales of the YOLOv4 object detector. Building on our baseline multiscale DAYOLO framework, we introduce three novel deep learning architectures for a Domain Adaptation Network (DAN) that generates domain-invariant features. In particular, we propose a Progressive Feature Reduction (PFR), a Unified Classifier (UC), and an Integrated architecture. We train and test our proposed DAN architectures in conjunction with YOLOv4 using popular datasets. Our experiments show significant improvements in object detection performance when training YOLOv4 using the proposed MS-DAYOLO architectures and when tested on target data for autonomous driving applications. Moreover, MS-DAYOLO framework achieves an order of magnitude real-time speed improvement relative to Faster R-CNN solutions while providing comparable object detection performance.

Multilevel Heterogeneous Domain Adaptation Method for Remote Sensing Image Segmentation

Due to more abundant data sources, more various objects of interest, and more time-consuming annotations, there is a large amount of out-of-distribution (OOD) data in the remote sensing field, on which the performance of high-accuracy image segmentation models trained under ideal experimental conditions generally degrades dramatically. Domain adaptation (DA) consequently comes into being, which aims to learn the predictor for the label-scarce target domain of interest with the help of the label-sufficient source domain in the presence of the distribution difference, namely, domain shift, between the two domains. However, the off-the-shelf DA methods for image segmentation not only struggle to cope with the more complex domain shift problems in remote sensing imagery but also almost cannot process heterogeneous data directly without information loss. While the current heterogeneous DA methods mostly still rely on some supervision information from the target domain, which is typically inaccessible in the real world. To overcome these drawbacks, we propose the multilevel heterogeneous unsupervised DA (UDA) method, termed MHDA, which unifies the instance-level DA based on cycle consistency, the feature-level DA based on contrastive learning, and the decision-level DA based on task consistency into a framework to more effectively handle the complex domain shift and heterogeneous data. After that, extensive DA experiments are conducted on the International Society for Photogrammetry and Remote Sensing (ISPRS) dataset, the BigCity dataset constructed by ourselves, and the Wuhan University (WHU) dataset, to explore the effect of each module in MHDA, the necessity of heterogeneous DA, and the effectiveness of multilevel DA. And the results demonstrate that MHDA can achieve superior performance on the remote sensing image segmentation task, compared with several state-of-the-art DA methods.

An End-to-End Approach for Rigid-Body Target Micro-Doppler Analysis Based on the Asymmetrical Autoencoding Network

Micro-Doppler analysis of rigid-body target is significant for attitude estimation and recognition of space objects. The traditional micro-Doppler analysis method for rigid-body targets includes two sequential steps. First, the time-frequency analysis is performed on the radar echo data of the target, and then the micro-Doppler curve of each scattering center is separated and extracted from the time-frequency map. The second step depends on the micro motion model of the target. In the micro-Doppler analysis of real rigid-body target, there are some problems such as the mismatch of the micro motion model, the incidence angle dependence of the scattering center position, and the partial occlusion of the scattering center. Therefore, it is very difficult to correctly extract the micro-Doppler curves of multiple scatterers. In this paper, an end-to-end micro-Doppler analysis method for rigid-body target based on deep learning network is proposed, which can directly separate and extract the micro-Doppler curves of multiple scatterers from the target echo data. Specifically, an Asymmetrical AutoEncoding (A2E) network equipped with a Data Pre-Processing (DP2) module is developed to extract Time-Frequency Curves (TFCs) from radar echos. Considering the sparseness of Time-Frequency Distribution (TFDs), we then develop a novel Energy-Concentration Objective (ECO) function based on Min-Max game to enhance curves energy while suppress the background energy. In practice, measured TFDs are rarely annotated, it restricts the generalization capability of the A2E from the simulation to the measurement. To bridge the gap, two-fold modifications are finally constructed: i) we insert a partial-shared branch of decoder to reconstruct the TFD from the DP2 module; ii) we regularize the ECO function with a knowledge preservation based reconstruction bound to further capture the characteristics of measured echos in a semi-supervised way at test time to relieve the domain-shift problem.

Dynamic classifier approximation for unsupervised domain adaptation

In recent years, domain adaptation (DA) method has been proposed to solve the problem of domain shift between the training set and test set. However, most feature-based unsupervised domain adaptation methods have a weakness of strict requirement on the transformation matrix and they are not integrated with classifier. Therefore, this paper proposes a novel dynamic classifier approximation (DCA) method for unsupervised domain adaptation. Specifically, the proposed DCA, which combines classifier method to relax the requirements of transformation matrix, learns domain invariant features from structure and data level. 1) At the structure level, the low-rank representation, sparse representation and manifold learning are combined to preserve the structure information of data in the original feature space. 2) At the data level, distribution alignments are adopted to minimize the distribution difference of the source and target domains in the common subspace, which is helpful to reduce the negative impact caused by domain shift. In addition, for learning the common subspace more flexibly, a dynamic classifier is introduced to reduce the strict requirements on projection matrix. This paper carries out a large number of experiments on four data sets, and the experimental results show that the proposed method is superior to many of the latest domain adaptation methods, which can indicate its effectiveness.