Low-Rank Optimal Transport for Robust Domain Adaptation

When encountering the distribution shift between the source(training) and target(test) domains, domain adaptation attempts to adjust the classifiers to be capable of dealing with different domains. Previous domain adaptation research has achieved a lot of success both in theory and practice under the assumption that all the examples in the source domain are welllabeled and of high quality. However, the methods consistently lose robustness in noisy settings where data from the source domain have corrupted labels or features which is common in reality. Therefore, robust domain adaptation has been introduced to deal with such problems. In this paper, we attempt to solve two interrelated problems with robust domain adaptation:distribution shift across domains and sample noises of the source domain. To disentangle these challenges, an optimal transport approach with low-rank constraints is applied to guide the domain adaptation model training process to avoid noisy information influence. For the domain shift problem, the optimal transport mechanism can learn the joint data representations between the source and target domains using a measurement of discrepancy and preserve the discriminative information. The rank constraint on the transport matrix can help recover the corrupted subspace structures and eliminate the noise to some extent when dealing with corrupted source data. The solution to this relaxed and regularized optimal transport framework is a convex optimization problem that can be solved using the Augmented Lagrange Multiplier method, whose convergence can be mathematically proved. The effectiveness of the proposed method is evaluated through extensive experiments on both synthetic and real-world datasets.

Diabetic retinopathy identification based on multi-sourcefree domain adaptation

AIM:To address the challenges of data labeling difficulties,data privacy,and necessary large amount of labeled data for deep learning methods in diabetic retinopathy(DR)identification,the aim of this study is to develop a source-free domain adaptation(SFDA)method for efficient and effective DR identification from unlabeled data.METHODS:A multi-SFDA method was proposed for DR identification.This method integrates multiple source models,which are trained from the same source domain,to generate synthetic pseudo labels for the unlabeled target domain.Besides,a softmax-consistence minimization term is utilized to minimize the intra-class distances between the source and target domains and maximize the inter-class distances.Validation is performed using three color fundus photograph datasets(APTOS2019,DDR,and EyePACS).RESULTS:The proposed model was evaluated and provided promising results with respectively 0.8917 and 0.9795 F1-scores on referable and normal/abnormal DR identification tasks.It demonstrated effective DR identification through minimizing intra-class distances and maximizing inter-class distances between source and target domains.CONCLUSION:The multi-SFDA method provides an effective approach to overcome the challenges in DR identification.The method not only addresses difficulties in data labeling and privacy issues,but also reduces the need for large amounts of labeled data required by deep learning methods,making it a practical tool for early detection and preservation of vision in diabetic patients.

Complementary-Label Adversarial Domain Adaptation Fault Diagnosis Network under Time-Varying Rotational Speed and Weakly-Supervised Conditions

Recent research in cross-domain intelligence fault diagnosis of machinery still has some problems,such as relatively ideal speed conditions and sample conditions.In engineering practice,the rotational speed of the machine is often transient and time-varying,which makes the sample annotation increasingly expensive.Meanwhile,the number of samples collected from different health states is often unbalanced.To deal with the above challenges,a complementary-label(CL)adversarial domain adaptation fault diagnosis network(CLADAN)is proposed under time-varying rotational speed and weakly-supervised conditions.In the weakly supervised learning condition,machine prior information is used for sample annotation via cost-friendly complementary label learning.A diagnosticmodel learning strategywith discretized category probabilities is designed to avoidmulti-peak distribution of prediction results.In adversarial training process,we developed virtual adversarial regularization(VAR)strategy,which further enhances the robustness of the model by adding adversarial perturbations in the target domain.Comparative experiments on two case studies validated the superior performance of the proposed method.

Bearing Fault Diagnosis Based on Deep Discriminative Adversarial Domain Adaptation Neural Networks

Intelligent diagnosis driven by big data for mechanical fault is an important means to ensure the safe operation ofequipment. In these methods, deep learning-based machinery fault diagnosis approaches have received increasingattention and achieved some results. It might lead to insufficient performance for using transfer learning alone andcause misclassification of target samples for domain bias when building deep models to learn domain-invariantfeatures. To address the above problems, a deep discriminative adversarial domain adaptation neural networkfor the bearing fault diagnosis model is proposed (DDADAN). In this method, the raw vibration data are firstlyconverted into frequency domain data by Fast Fourier Transform, and an improved deep convolutional neuralnetwork with wide first-layer kernels is used as a feature extractor to extract deep fault features. Then, domaininvariant features are learned from the fault data with correlation alignment-based domain adversarial training.Furthermore, to enhance the discriminative property of features, discriminative feature learning is embeddedinto this network to make the features compact, as well as separable between classes within the class. Finally, theperformance and anti-noise capability of the proposedmethod are evaluated using two sets of bearing fault datasets.The results demonstrate that the proposed method is capable of handling domain offset caused by differentworkingconditions and maintaining more than 97.53% accuracy on various transfer tasks. Furthermore, the proposedmethod can achieve high diagnostic accuracy under varying noise levels.

Enhancing Unsupervised Domain Adaptation for Person Re-Identification with the Minimal Transfer Cost Framework

In Unsupervised Domain Adaptation(UDA)for person re-identification(re-ID),the primary challenge is reducing the distribution discrepancy between the source and target domains.This can be achieved by implicitly or explicitly constructing an appropriate intermediate domain to enhance recognition capability on the target domain.Implicit construction is difficult due to the absence of intermediate state supervision,making smooth knowledge transfer from the source to the target domain a challenge.To explicitly construct the most suitable intermediate domain for the model to gradually adapt to the feature distribution changes from the source to the target domain,we propose the Minimal Transfer Cost Framework(MTCF).MTCF considers all scenarios of the intermediate domain during the transfer process,ensuring smoother and more efficient domain alignment.Our framework mainly includes threemodules:Intermediate Domain Generator(IDG),Cross-domain Feature Constraint Module(CFCM),and Residual Channel Space Module(RCSM).First,the IDG Module is introduced to generate all possible intermediate domains,ensuring a smooth transition of knowledge fromthe source to the target domain.To reduce the cross-domain feature distribution discrepancy,we propose the CFCM Module,which quantifies the difficulty of knowledge transfer and ensures the diversity of intermediate domain features and their semantic relevance,achieving alignment between the source and target domains by incorporating mutual information and maximum mean discrepancy.We also design the RCSM,which utilizes attention mechanism to enhance the model’s focus on personnel features in low-resolution images,improving the accuracy and efficiency of person re-ID.Our proposed method outperforms existing technologies in all common UDA re-ID tasks and improves the Mean Average Precision(mAP)by 2.3%in the Market to Duke task compared to the state-of-the-art(SOTA)methods.

Multi-Modal Domain Adaptation Variational Autoencoder for EEG-Based Emotion Recognition

Traditional electroencephalograph(EEG)-based emotion recognition requires a large number of calibration samples to build a model for a specific subject,which restricts the application of the affective brain computer interface(BCI)in practice.We attempt to use the multi-modal data from the past session to realize emotion recognition in the case of a small amount of calibration samples.To solve this problem,we propose a multimodal domain adaptive variational autoencoder(MMDA-VAE)method,which learns shared cross-domain latent representations of the multi-modal data.Our method builds a multi-modal variational autoencoder(MVAE)to project the data of multiple modalities into a common space.Through adversarial learning and cycle-consistency regularization,our method can reduce the distribution difference of each domain on the shared latent representation layer and realize the transfer of knowledge.Extensive experiments are conducted on two public datasets,SEED and SEED-IV,and the results show the superiority of our proposed method.Our work can effectively improve the performance of emotion recognition with a small amount of labelled multi-modal data.

Dynamic Distribution Adaptation Based Transfer Network for Cross Domain Bearing Fault Diagnosis

In machinery fault diagnosis,labeled data are always difficult or even impossible to obtain.Transfer learning can leverage related fault diagnosis knowledge from fully labeled source domain to enhance the fault diagnosis performance in sparsely labeled or unlabeled target domain,which has been widely used for cross domain fault diagnosis.However,existing methods focus on either marginal distribution adaptation(MDA)or conditional distribution adaptation(CDA).In practice,marginal and conditional distributions discrepancies both have significant but different influences on the domain divergence.In this paper,a dynamic distribution adaptation based transfer network(DDATN)is proposed for cross domain bearing fault diagnosis.DDATN utilizes the proposed instance-weighted dynamic maximum mean discrepancy(IDMMD)for dynamic distribution adaptation(DDA),which can dynamically estimate the influences of marginal and conditional distribution and adapt target domain with source domain.The experimental evaluation on cross domain bearing fault diagnosis demonstrates that DDATN can outperformance the state-of-the-art cross domain fault diagnosis methods.

Tomato detection method using domain adaptive learning for dense planting environments

This study aimed to address the challenge of accurately and reliably detecting tomatoes in dense planting environments,a critical prerequisite for the automation implementation of robotic harvesting.However,the heavy reliance on extensive manually annotated datasets for training deep learning models still poses significant limitations to their application in real-world agricultural production environments.To overcome these limitations,we employed domain adaptive learning approach combined with the YOLOv5 model to develop a novel tomato detection model called as TDA-YOLO(tomato detection domain adaptation).We designated the normal illumination scenes in dense planting environments as the source domain and utilized various other illumination scenes as the target domain.To construct bridge mechanism between source and target domains,neural preset for color style transfer is introduced to generate a pseudo-dataset,which served to deal with domain discrepancy.Furthermore,this study combines the semi-supervised learning method to enable the model to extract domain-invariant features more fully,and uses knowledge distillation to improve the model's ability to adapt to the target domain.Additionally,for purpose of promoting inference speed and low computational demand,the lightweight FasterNet network was integrated into the YOLOv5's C3 module,creating a modified C3_Faster module.The experimental results demonstrated that the proposed TDA-YOLO model significantly outperformed original YOLOv5s model,achieving a mAP(mean average precision)of 96.80%for tomato detection across diverse scenarios in dense planting environments,increasing by 7.19 percentage points;Compared with the latest YOLOv8 and YOLOv9,it is also 2.17 and 1.19 percentage points higher,respectively.The model's average detection time per image was an impressive 15 milliseconds,with a FLOPs(floating point operations per second)count of 13.8 G.After acceleration processing,the detection accuracy of the TDA-YOLO model on the Jetson Xavier NX development board is 90.95%,the mAP value is 91.35%,and the detection time of each image is 21 ms,which can still meet the requirements of real-time detection of tomatoes in dense planting environment.The experimental results show that the proposed TDA-YOLO model can accurately and quickly detect tomatoes in dense planting environment,and at the same time avoid the use of a large number of annotated data,which provides technical support for the development of automatic harvesting systems for tomatoes and other fruits.

Inversion of Seabed Geotechnical Properties in the Arctic Chukchi Deep Sea Basin Based on Time Domain Adaptive Search Matching Algorithm

The chirp sub-bottom profiler,for its high resolution,easy accessibility and cost-effectiveness,has been widely used in acoustic detection.In this paper,the acoustic impedance and grain size compositions were obtained based on the chirp sub-bottom profiler data collected in the Chukchi Plateau area during the 11th Arctic Expedition of China.The time-domain adaptive search matching algorithm was used and validated on our established theoretical model.The misfit between the inversion result and the theoretical model is less than 0.067%.The grain size was calculated according to the empirical relationship between the acoustic impedance and the grain size of the sediment.The average acoustic impedance of sub-seafloor strata is 2.5026×10^(6) kg(s m^(2))^(-1)and the average grain size(θvalue)of the seafloor surface sediment is 7.1498,indicating the predominant occurrence of very fine silt sediment in the study area.Comparison of the inversion results and the laboratory measurements of nearby borehole samples shows that they are in general agreement.

RECONSTRUCTION OF ONE DIMENSIONAL MULTI-LAYERED MEDIA BY USING A TIME DOMAIN SIGNAL FLOW GRAPH TECHNIQUE

A novel inverse scattering method to reconstruct the permittivity profile of one-dimensional multi-layered media is proposed in this paper.Based on the equivalent network ofthe medium,a concept of time domain signal flow graph and its basic principles are introduced,from which the reflection coefficient of the medium in time domain can be shown to be a series ofDirac δ-functions(pulse responses).In terms of the pulse responses,we will reconstruct both thepermittivity and the thickness of each layer will accurately be reconstructed.Numerical examplesverify the applicability of this

Unsupervised Domain Adaptation Based on Discriminative Subspace Learning for Cross-Project Defect Prediction

:Cross-project defect prediction(CPDP)aims to predict the defects on target project by using a prediction model built on source projects.The main problem in CPDP is the huge distribution gap between the source project and the target project,which prevents the prediction model from performing well.Most existing methods overlook the class discrimination of the learned features.Seeking an effective transferable model from the source project to the target project for CPDP is challenging.In this paper,we propose an unsupervised domain adaptation based on the discriminative subspace learning(DSL)approach for CPDP.DSL treats the data from two projects as being from two domains and maps the data into a common feature space.It employs crossdomain alignment with discriminative information from different projects to reduce the distribution difference of the data between different projects and incorporates the class discriminative information.Specifically,DSL first utilizes subspace learning based domain adaptation to reduce the distribution gap of data between different projects.Then,it makes full use of the class label information of the source project and transfers the discrimination ability of the source project to the target project in the common space.Comprehensive experiments on five projects verify that DSL can build an effective prediction model and improve the performance over the related competing methods by at least 7.10%and 11.08%in terms of G-measure and AUC.

Knowledge Transfer Learning via Dual Density Sampling for Resource-Limited Domain Adaptation

Most existing domain adaptation(DA) methods aim to explore favorable performance under complicated environments by sampling.However,there are three unsolved problems that limit their efficiencies:ⅰ) they adopt global sampling but neglect to exploit global and local sampling simultaneously;ⅱ)they either transfer knowledge from a global perspective or a local perspective,while overlooking transmission of confident knowledge from both perspectives;and ⅲ) they apply repeated sampling during iteration,which takes a lot of time.To address these problems,knowledge transfer learning via dual density sampling(KTL-DDS) is proposed in this study,which consists of three parts:ⅰ) Dual density sampling(DDS) that jointly leverages two sampling methods associated with different views,i.e.,global density sampling that extracts representative samples with the most common features and local density sampling that selects representative samples with critical boundary information;ⅱ)Consistent maximum mean discrepancy(CMMD) that reduces intra-and cross-domain risks and guarantees high consistency of knowledge by shortening the distances of every two subsets among the four subsets collected by DDS;and ⅲ) Knowledge dissemination(KD) that transmits confident and consistent knowledge from the representative target samples with global and local properties to the whole target domain by preserving the neighboring relationships of the target domain.Mathematical analyses show that DDS avoids repeated sampling during the iteration.With the above three actions,confident knowledge with both global and local properties is transferred,and the memory and running time are greatly reduced.In addition,a general framework named dual density sampling approximation(DDSA) is extended,which can be easily applied to other DA algorithms.Extensive experiments on five datasets in clean,label corruption(LC),feature missing(FM),and LC&FM environments demonstrate the encouraging performance of KTL-DDS.

Estimating the State of Health for Lithium-ion Batteries:A Particle Swarm Optimization-Assisted Deep Domain Adaptation Approach

The state of health(SOH)is a critical factor in evaluating the performance of the lithium-ion batteries(LIBs).Due to various end-user behaviors,the LIBs exhibit different degradation modes,which makes it challenging to estimate the SOHs in a personalized way.In this article,we present a novel particle swarm optimization-assisted deep domain adaptation(PSO-DDA)method to estimate the SOH of LIBs in a personalized manner,where a new domain adaptation strategy is put forward to reduce cross-domain distribution discrepancy.The standard PSO algorithm is exploited to automatically adjust the chosen hyperparameters of developed DDA-based method.The proposed PSODDA method is validated by extensive experiments on two LIB datasets with different battery chemistry materials,ambient temperatures and charge-discharge configurations.Experimental results indicate that the proposed PSO-DDA method surpasses the convolutional neural network-based method and the standard DDA-based method.The Py Torch implementation of the proposed PSO-DDA method is available at https://github.com/mxt0607/PSO-DDA.

Unsupervised Domain Adaptation Learning Algorithm for RGB-D Stairway Recognition

Detection and recognition of a stairway as upstairs,downstairs and negative(e.g.,ladder,level ground)are the fundamentals of assisting the visually impaired to travel independently in unfamiliar environments.Previous studies have focused on using massive amounts of RGB-D scene data to train traditional machine learning(ML)-based models to detect and recognize stationary stairway and escalator stairway separately.Nevertheless,none of them consider jointly training these two similar but different datasets to achieve better performance.This paper applies an adversarial learning algorithm on the indicated unsupervised domain adaptation scenario to transfer knowledge learned from the labeled RGB-D escalator stairway dataset to the unlabeled RGB-D stationary dataset.By utilizing the developed method,a feedforward convolutional neural network(CNN)-based feature extractor with five convolution layers can achieve 100%classification accuracy on testing the labeled escalator stairway data distributions and 80.6%classification accuracy on testing the unlabeled stationary data distributions.The success of the developed approach is demonstrated for classifying stairway on these two domains with a limited amount of data.To further demonstrate the effectiveness of the proposed method,the same CNN model is evaluated without domain adaptation and the results are compared with those of the presented architecture.

Adaptive Graph Embedding With Consistency and Specificity for Domain Adaptation

Domain adaptation(DA) aims to find a subspace,where the discrepancies between the source and target domains are reduced. Based on this subspace, the classifier trained by the labeled source samples can classify unlabeled target samples well.Existing approaches leverage Graph Embedding Learning to explore such a subspace. Unfortunately, due to 1) the interaction of the consistency and specificity between samples, and 2) the joint impact of the degenerated features and incorrect labels in the samples, the existing approaches might assign unsuitable similarity, which restricts their performance. In this paper, we propose an approach called adaptive graph embedding with consistency and specificity(AGE-CS) to cope with these issues. AGE-CS consists of two methods, i.e., graph embedding with consistency and specificity(GECS), and adaptive graph embedding(AGE).GECS jointly learns the similarity of samples under the geometric distance and semantic similarity metrics, while AGE adaptively adjusts the relative importance between the geometric distance and semantic similarity during the iterations. By AGE-CS,the neighborhood samples with the same label are rewarded,while the neighborhood samples with different labels are punished. As a result, compact structures are preserved, and advanced performance is achieved. Extensive experiments on five benchmark datasets demonstrate that the proposed method performs better than other Graph Embedding methods.

Semantic Constraint Based Unsupervised Domain Adaptation for Cardiac Segmentation

The segmentation of unlabeled medical images is troublesome due to the high cost of annotation, and unsupervised domain adaptation is one solution to this. In this paper, an improved unsupervised domain adaptation method was proposed. The proposed method considered both global alignment and category-wise alignment. First, we aligned the appearance of two domains by image transformation. Second, we aligned the output maps of two domains in a global way. Then, we decomposed the semantic prediction map by category, aligning the prediction maps in a category-wise manner. Finally, we evaluated the proposed method on the 2017 Multi-Modality Whole Heart Segmentation Challenge dataset, and obtained 82.1 on the dice similarity coefficient and 4.6 on the average symmetric surface distance, demonstrating the effectiveness of the combination of global alignment and category-wise alignment.

Defense against Membership Inference Attack Applying Domain Adaptation with Addictive Noise

Deep learning can train models from a dataset to solve tasks. Although deep learning has attracted much interest owing to the excellent performance, security issues are gradually exposed. Deep learning may be prone to the membership inference attack, where the attacker can determine the membership of a given sample. In this paper, we propose a new defense mechanism against membership inference: NoiseDA. In our proposal, a model is not directly trained on a sensitive dataset to alleviate the threat of membership inference attack by leveraging domain adaptation. Besides, a module called Feature Crafter has been designed to reduce the necessary training dataset from 2 to 1, which creates features for domain adaptation training using noise addictive mechanisms. Our experiments have shown that, with the noises properly added by Feature Crafter, our proposal can reduce the success of membership inference with a controllable utility loss.

Domain Adaptation for Synthesis of Hazy Images

Most existing image dehazing methods based learning are less able to perform well to real hazy images. An important reason is that they are trained on synthetic hazy images whose distribution is different from real hazy images. To relieve this issue, this paper proposes a new hazy scene generation model based on domain adaptation, which uses a variational autoencoder to encode the synthetic hazy image pairs and the real hazy images into the latent space to adapt. The synthetic hazy image pairs guide the model to learn the mapping of clear images to hazy images, the real hazy images are used to adapt the synthetic hazy images’ latent space to real hazy images through generative adversarial loss, so as to make the generative hazy images’ distribution as close to the real hazy images’ distribution as possible. By comparing the results of the model with traditional physical scattering models and Adobe Lightroom CC software, the hazy images generated in this paper is more realistic. Our end-to-end domain adaptation model is also very convenient to synthesize hazy images without depth map. Using traditional method to dehaze the synthetic hazy images generated by this paper, both SSIM and PSNR have been improved, proved that the effectiveness of our method. The non-reference haze density evaluation algorithm and other quantitative evaluation also illustrate the advantages of our method in synthetic hazy images.

Bilateral co-transfer for unsupervised domain adaptation

Labeled data scarcity of an interested domain is often a serious problem in machine learning.Leveraging the labeled data from other semantic-related yet co-variate shifted source domain to facilitate the interested domain is a consensus.In order to solve the domain shift between domains and reduce the learning ambiguity,unsupervised domain adaptation(UDA)greatly promotes the transferability of model parameters.However,the dilemma of over-fitting(negative transfer)and under-fitting(under-adaptation)is always an overlooked challenge and potential risk.In this paper,we rethink the shallow learning paradigm and this intractable over/under-fitting problem,and propose a safer UDA model,coined as Bilateral Co-Transfer(BCT),which is essentially beyond previous well-known unilateral transfer.With bilateral co-transfer between domains,the risk of over/under-fitting is therefore largely reduced.Technically,the proposed BCT is a symmetrical structure,with joint distribution discrepancy(JDD)modeled for domain alignment and category discrimination.Specifically,a symmetrical bilateral transfer(SBT)loss between source and target domains is proposed under the philosophy of mutual checks and balances.First,each target sample is represented by source samples with low-rankness constraint in a common subspace,such that the most informative and transferable source data can be used to alleviate negative transfer.Second,each source sample is symmetrically and sparsely represented by target samples,such that the most reliable target samples can be exploited to tackle underadaptation.Experiments on various benchmarks show that our BCT outperforms many previous outstanding work.

Balanced Discriminative Transfer Feature Learning for Visual Domain Adaptation

Transfer learning aims to transfer source models to a target domain.Leveraging the feature matching can alleviate the domain shift effectively,but this process ignores the relationship of the marginal distribution matching and the conditional distribution matching.Simultaneously,the discriminative information of both domains is also neglected,which is important for improving the performance on the target domain.In this paper,we propose a novel method called Balanced Discriminative Transfer Feature Learning for Visual Domain Adaptation(BDTFL).The proposed method can adaptively balance the relationship of both distribution matchings and capture the category discriminative information of both domains.Therefore,balanced feature matching can achieve more accurate feature matching and adaptively adjust itself to different scenes.At the same time,discriminative information is exploited to alleviate category confusion during feature matching.And with assistance of the category discriminative information captured from both domains,the source classifier can be transferred to the target domain more accurately and boost the performance of target classification.Extensive experiments show the superiority of BDTFL on popular visual cross-domain benchmarks.