Domain-invariant Representations Research Articles

Progressive de-preference task-specific processing for generalizable person re-identification

Recently, domain generalization (DG) person re-identification (ReID) has attracted attention. Existing DG person ReID methods train on mixed datasets containing all source domains. However, these mixed datasets have huge inter-domain differences because of varying data distributions across different source domains. Such differences hinder models from learning domain-invariant representations, affecting generalization on unseen domains. To address this issue, we propose a progressive de-preference task-specific processing network (PDTP-Net) for DG person ReID. Initially, we design a progressive de-preference domain segmentation strategy to mitigate inter-domain differences by dividing multiple source domains into different phases, each comprising several training tasks. We then design a global and task-specific processing module that enhances extraction of domain-invariant features by integrating statistical information from other source domains. Finally, we design a multi-granularity attention module and a group-aware batch normalization strategy to ensure the features are more discriminative and better suited for person ReID tasks. The proposed model is validated using three DG person ReID experimental protocols: Protocol-1, Protocol-2, and leave-one-out experiments. On Protocol-1, the model improves mean average precision (mAP) and Rank-1 accuracy on all datasets by an average of 0.7% and 0.3%, respectively. On Protocol-2, the model improves mAP and Rank-1 accuracy on all datasets by an average of 2.525% and 2.725%, respectively. On the leave-one-out experiments, the model improves mAP and Rank-1 accuracy on all tasks by an average of 0.65% and 0.18%, respectively. The results on several popular datasets suggest that the model achieves state-of-the-art performance in DG person ReID.

Camera-aware graph multi-domain adaptive learning for unsupervised person re-identification

Recently, unsupervised person re-identification (Re-ID) has gained much attention due to its important practical significance in real-world application scenarios without pairwise labeled data. A key challenge for unsupervised person Re-ID is learning discriminative and robust feature representations under cross-camera scene variation. Contrastive learning approaches treat unsupervised representation learning as a dictionary look-up task. However, existing methods ignore both intra- and inter-camera semantic associations during training. In this paper, we propose a novel unsupervised person Re-ID framework, Camera-Aware Graph Multi-Domain Adaptive Learning (CGMAL), which can conduct multi-domain feature transfer with semantic propagation for learning discriminative domain-invariant representations. Specifically, we treat each camera as a distinct domain and extract image samples from every camera domain to form a mini-batch. A heterogeneous graph is constructed for representing the relationships between all instances in a mini-batch. Then a Graph Convolutional Network (GCN) is employed to fuse the image samples into a unified space and implement promising semantic transfer for providing ideal feature representations. Subsequently, we construct the memory-based non-parametric contrastive loss to train the model. In particular, we design an adversarial training scheme for transferring the knowledge learned by GCN to the feature extractor. Experimental experiments on three benchmarks validate that our proposed approach is superior to the state-of-the-art unsupervised methods.

A Latent Representation Generalizing Network for Domain Generalization in Cross-Scenario Monitoring.

Cross-scenario monitoring requires domain generalization (DG) for changed knowledge when auxiliary information is unavailable and only one source scenario is involved. In this article, a latent representation generalizing network (LRGN) is proposed to learn transferable knowledge through generalizing the latent representations for cross-scenario monitoring in perimeter security. LRGN is composed of a sequential-variational generative adversarial network (SVGAN), a coupled SVGAN (Co-SVGAN), and a knowledge-aggregated SVGAN. First, the Co-SVGAN can learn domain-invariant latent representations to model dual-domain joint distribution of background data, which is usually sufficient in the source and target scenarios. Deceptive domain shifts are generated based on the domain-invariant latent representations without auxiliary information. Then, SVGAN models the changing knowledge by estimating the distribution of domain shifts. Furthermore, the knowledge-aggregated SVGAN can transfer the learned domain-invariant knowledge from Co-SVGAN for generalizing the latent representations through approximating the distribution of domain shifts. Accordingly, LRGN is trained by a four-phase optimization strategy for DG through generating target-scenario samples of concerned events based on the generalized latent representations. The feasibility and effectiveness of the proposed method are validated through real-field experiments of perimeter security applications in two scenarios.

Learn to Adapt for Self-Supervised Monocular Depth Estimation.

Monocular depth estimation is one of the fundamental tasks in environmental perception and has achieved tremendous progress by virtue of deep learning. However, the performance of trained models tends to degrade or deteriorate when employed on other new datasets due to the gap between different datasets. Though some methods utilize domain adaptation technologies to jointly train different domains and narrow the gap between them, the trained models cannot generalize to new domains that are not involved in training. To boost the transferability of self-supervised monocular depth estimation models and mitigate the issue of meta-overfitting, we train the model in the pipeline of meta-learning and propose an adversarial depth estimation task. We adopt model-agnostic meta-learning (MAML) to obtain universal initial parameters for further adaptation and train the network in an adversarial manner to extract domain-invariant representations for easing meta-overfitting. In addition, we propose a constraint to impose upon cross-task depth consistency to compel the depth estimation to be identical in different adversarial tasks, which improves the performance of our method and smoothens the training process. Experiments on four new datasets demonstrate that our method adapts quite fast to new domains. Our method trained after 0.5 epoch achieves comparable results with the state-of-the-art methods trained at least 20 epochs.

A domain generalization network for imbalanced machinery fault diagnosis

Traditional models for Imbalanced Fault Diagnosis (IFD) face challenges in practical applications due to domain shifts caused by varying working conditions and machinery. Domain Generalization (DG) models provide an advantage over traditional approaches by learning class-discriminative and domain-invariant feature representations, allowing them to generalize to unseen target data. However, the scarcity of fault samples relative to healthy ones limits their application in real-world industrial scenarios. In this paper, we propose a Domain Mixed-Enhanced Domain Generalization Network (DEMDGN) that enhances IFD performance by utilizing mixup-based data augmentation and domain-based discrepancy metrics to align feature distributions across multiple heterogeneous source domains. By creating domain-invariant features, DEMDGN allows robust fault diagnosis under varying conditions. Extensive experiments on one marine machinery dataset and two bearing datasets demonstrate that the proposed method effectively addresses class imbalance and domain shift problems, achieving superior diagnostic performance.

Considering representation diversity and prediction consistency for domain generalization semantic segmentation

Existing domain generalization semantic segmentation (DGSS) methods aim to learn domain-invariant representation from single or multiple domains by using the consistency constraint or normalization strategy. Although these methods can improve the generalization capability of the models, the representation capability may be inevitably weakened since some effective information is eliminated, which may lead to the low discrimination capability of models. To simultaneously preserve the generalization and discrimination capability of models, we provide a novel perspective that encourages to learn the distinct representation while keeping the consistent prediction. Based on this, we propose a novel approach for domain generalization semantic segmentation by simultaneously considering the representation diversity and prediction consistency. The proposed approach consists of an adaptive style randomization (ASR) module, a representation diversity (RD) constraint, and a prediction consistency (PC) constraint. Specifically, first, since diverse stylized images are beneficial for the RD constraint to learn the distinct representation, the ASR module is proposed to leverage global and local style randomization to generate diverse stylized images which have the same content as the source domain images. Then, the distinct representation is learned from the source domain images and the stylized images by using the RD constraint to improve the discrimination capability of the model. Finally, the distinct representation is expected to generate consistent prediction by using the PC constraint for preserving the generalization capability of the model. Extensive experiments demonstrate that our approach achieves superior performance over current approaches on several benchmarks.

Unsupervised multi-source domain adaptation via contrastive learning for EEG classification

Individual differences in electroencephalography (EEG) present significant challenges for subject-independent EEG classification in brain–computer interfaces (BCIs). Existing domain adaptation methods often address individual differences by merging all source domains indistinguishably into a single source and aligning features between this aggregate source and the target domain. Neglecting the relationships between different source domains would hinder the model’s adaptability and generalization. Therefore, we propose a method called Contrastive Learning-based Unsupervised multi-source Domain Adaptation (CLUDA) for learning subject-independent representations in motor imagery. Our method not only aligns the conditional distributions of each source domain with the target domain but also reduces discrepancies among the source domains using contrastive learning, thus learning more generalized domain-invariant representations. Specifically, CLUDA effectively eliminates semantic variances by maximizing the similarity between positive pairs (same class) and minimizing the similarity between negative pairs (different classes) across subjects. Finally, we validated CLUDA on four motor imagery datasets and consistently achieved state-of-the-art performance.

Hierarchical Keypoints Feature Alignment for Domain Adaptive Pose Estimation

Unsupervised Domain Adaptation (UDA) is a popular research topic in computer vision. One of the most common strategies in this field is to reduce domain shifts through global feature alignment. Unfortunately, we observe its failure on adaptive human pose estimation. From our analysis, we find out two major reasons: the extreme imbalance between keypoints and non-keypoints regions and the high diversity of human skeleton structures. To address these problems, we propose a simple yet effective approach named PoseDA. Our idea is to let the alignment focus on the feature of keypoint regions and enforce the model to learn domain-invariant representations for keypoint prediction. The key component of our PoseDA is a Hierarchical Feature Selection of Keypoints Regions (HFS) module, which consists of Coarse Feature Selection of Keypoints Regions (CFS) and Reliable Feature Selection of Keypoints Regions (RFS). By using HFS, we obtain reliable and compact keypoints features, allowing our model to achieve more effective feature alignment. Under three UDA scenarios, i.e. JTA→MPII, SURREAL→LSP, SURREAL→Human3.6, our PoseDA establishes new state-of-the-art performance. In particular, our PoseDA outperforms the previous best UDA methods by over 7% w.r.t. PCKh on JTA→MPII.

A two-layer regression network for robust and accurate domain adaptation

Naturally, classification models suffer from severe performance degradation when they are tested on datasets different from the ones used in training. Unsupervised domain adaptation helps to improve the generalizability of a pre-trained model by transferring knowledge from the labeled source domain (i.e., training dataset) to the unlabeled target domain (i.e., test dataset). The typical way of domain adaptation is to align the data distributions in embedding spaces between source and target domains. However, most existing works only enhance cross-domain consistency in the latent space disregarding the impact of source samples on the target classification task. Besides, discovering a subspace shared by two domains first and then training a transfer classifier separately hardly ensures that the obtained target features are suited for the classification model. To address these issues, in this work, we propose a two-layer regression network for domain adaptation (TRN-DA). TRN-DA learns class-wise domain invariant feature representations by jointly optimizing three tasks: supervised classification of source domain, unsupervised reconstruction of target domain, and alignment of cross-domain distributions. Furthermore, we introduce the concept of weight (importance) for source instances so that the resulting classifier can adapt well to the target domain. We formulate the domain adaptation problem as a unified optimization problem and solve it in an iterative way. Experimental results on different cross-domain image classification tasks demonstrate the encouraging performance of our TRN-DA compared to several recent state-of-the-art methods.

A Domain Generation Diagnosis Framework for Unseen Conditions Based on Adaptive Feature Fusion and Augmentation

Emerging deep learning-based fault diagnosis methods have advanced in the current industrial scenarios of various working conditions. However, the prerequisite of obtaining target data in advance limits the application of these models to practical engineering scenarios. To address the challenge of fault diagnosis under unseen working conditions, a domain generation framework for unseen conditions fault diagnosis is proposed, which consists of an Adaptive Feature Fusion Domain Generation Network (AFFN) and a Mix-up Augmentation Method (MAM) for both the data and domain spaces. AFFN is utilized to fuse domain-invariant and domain-specific representations to improve the model’s generalization performance. MAM enhances the model’s exploration ability for unseen domain boundaries. The diagnostic framework with AFFN and MAM can effectively learn more discriminative features from multiple source domains to perform different generalization tasks for unseen working loads and machines. The feasibility of the proposed unseen conditions diagnostic framework is validated on the SDUST and PU datasets and achieved peak diagnostic accuracies of 94.15% and 93.27%, respectively.

Time-series domain adaptation via sparse associative structure alignment: Learning invariance and variance

Domain adaptation on time-series data, which is often encountered in the field of industry, like anomaly detection and sensor data forecasting, but received limited attention in academia, is an important but challenging task in real-world scenarios. Most of the existing methods for time-series data use the covariate shift assumption for non-time-series data to extract the domain-invariant representation, but this assumption is hard to meet in practice due to the complex dependence among variables and a small change of the time lags may lead to a huge change of future values. To address this challenge, we leverage the stableness of causal structures among different domains. To further avoid the strong assumptions in causal discovery like linear non-Gaussian assumption, we relax it to mine the stable sparse associative structures instead of discovering the causal structures directly. Besides the domain-invariant structures, we also find that some domain-specific information like the strengths of the structures is important for prediction. Based on the aforementioned intuition, we extend the sparse associative structure alignment model in the conference version to the Sparse Associative Structure Alignment model with domain-specific information enhancement (SASA2 in short), which aligns the invariant unweighted spare associative structures and considers the variant information for time-series unsupervised domain adaptation. Specifically, we first generate the segment set to exclude the obstacle of offsets. Second, we extract the unweighted sparse associative structures via sparse attention mechanisms. Third, we extract the domain-specific information via an autoregressive module. Finally, we employ a unidirectional alignment restriction to guide the transformation from the source to the target. Moreover, we further provide a generalization analysis to show the theoretical superiority of our method. Compared with existing methods, our method yields state-of-the-art performance, with a 5% relative improvement in three real-world datasets, covering different applications: air quality, in-hospital healthcare, and anomaly detection. Furthermore, visualization results of sparse associative structures illustrate what knowledge can be transferred, boosting the transparency and interpretability of our method.

A bidirectional domain separation adversarial network based transfer learning method for near-infrared spectra

Traditional calibration transfer (CT) methods usually fail to adapt the source domain model to the target domain because of changes associated with the instrument, detection environment, sample composition, or sample type. Most deep transfer learning (DTL) methods have shown reliable capability in extracting domain-invariant representations. However, factors unique to the spectral domain limit their development and application, including difficulty in obtaining labeled samples, numerous spectral perturbation factors, and the scarcity of spectral databases. To address these challenges, we here introduce the Bidirectional Domain-Separating Adversarial Network (BiDSAN), based on a deep adversarial network transfer architecture, for learning and adapting to distribution/domain differences between sample spectra. BiDSAN incorporates Wasserstein divergence (w-div) and dynamic adversarial factor into the domain critic (discriminator) to accelerate the extraction of spectral shared components. Additionally, the use of the spectral signal distortion ratio as a loss function and the introduction of a bidirectional mechanism further enhanced the training accuracy and speed of spectral models. Calibration analyses were tested on pharmaceutical and two sets of wood datasets, corresponding to three common domain/distribution difference scenarios discussed in the study. Compared to existing CT and DTL methods, the proposed BiDSAN method demonstrated superior spectral signal calibration capability and stability, achieving unsupervised domain adaptation for similar samples and, for the first time, obtaining ideal prediction results in cross-species spectral domain adaptation. Our method represents significant potential for using DTL approaches in spectral domain adaptation.

Domain generalization via causal fine-grained feature decomposition and learning

Domain generalization aims to accurately predict unknown data using models trained by known domain data. Learning domain-invariant representations based on causal inference is one of the popular directions in domain generalization. However, existing domain generalization models based on causal inference cannot correctly determine the invariance conditions of the data. It is because of the interdependent relationship between domain-invariant features and confounding factors that ultimately leads to difficulty in obtaining truly invariant representations by the model. In this paper, we propose a novel domain generalization method called causal fine-grained feature decomposition and learning (CFFDL), which aims to eliminate latent confounding factors and learn causal domain-invariant representations in image classification tasks. Specifically, we design a feature decomposition module based on mutual information, which can decompose deep features into fine-grained feature factors and achieve factor independence between different dimensions, thereby helping to eliminate confounding factors. Furthermore, we introduce a causal representations learning module that can effectively filter and extract relevant causal features of the prediction task while eliminating the influence of confounding factors, improving the model’s performance on domain generalization. Extensive experiments on three domain generalization datasets VLCS, PACS and Office–Home show that our method outperforms the current state-of-the-art models, proving its effectiveness and superiority on domain generalization tasks of image classification.

Disentanglement-inspired single-source domain-generalization network for cross-scene hyperspectral image classification

Cross-scene classification stands as a pivotal frontier in hyperspectral image (HSI) processing, aiming to enhance the generalization capabilities of classification models. However, the diversity of sensor type, shooting environments, and shooting times leads to the spectral heterogeneity problem in HSI. As a result, the same land cover may exhibit varying spectral traits in different domains, posing challenges for cross-scene HSI classification. Drawing inspiration from image disentanglement, we have identified that extracting the latent domain-invariant representation (DIR) of HSI could potentially mitigate the spectral heterogeneity issue. Therefore, we propose a Disentanglement-Inspired Single-Source Domain Generalization Network (DSDGnet) for cross-scene HSI classification in this paper. Firstly, a style transfer module based on a Transformer encoder-transfer-decoder is designed to expand the single source domain to an extended domain. Then, a progressive disentanglement module is proposed to decompose the domain-invariant features and domain-specific features of HSI. Furthermore, a domain combination module is designed to guarantee the accuracy of the progressive disentanglement module and ensure the effectiveness of the domain-invariant feature of HSI. Finally, the domain-invariant features are applied to the classification task, and the domain-specific features are separated to reduce their impact on the generalization ability of classification models. Extensive experiments on three HSI datasets have demonstrated the advanced classification performance of DSDGnet compared to existing domain-generalization methods.

Mask-Shift-Inference: A novel paradigm for domain generalization

Domain Generalization (DG) focuses on the Out-Of-Distribution (OOD) generalization, which is able to learn a robust model that generalizes the knowledge acquired from the source domain to the unseen target domain. However, due to the existence of the domain shift, domain-invariant representation learning is challenging. Guided by fine-grained knowledge, we propose a novel paradigm Mask-Shift-Inference (MSI) for DG based on the architecture of Convolutional Neural Networks (CNN). Different from relying on a series of constraints and assumptions for model optimization, this paradigm novelly shifts the focus to feature channels in the latent space for domain-invariant representation learning. We put forward a two-branch working mode of a main module and multiple domain-specific sub-modules. The latter can only achieve good prediction performance in its own specific domain but poor predictions in other source domains, which provides the main module with the fine-grained knowledge guidance and contributes to the improvement of the cognitive ability of MSI. Firstly, during the forward propagation of the main module, the proposed MSI accurately discards unstable channels based on spurious classifications varying across domains, which have domain-specific prediction limitations and are not conducive to generalization. In this process, a progressive scheme is adopted to adaptively increase the masking ratio according to the training progress to further reduce the risk of overfitting. Subsequently, our paradigm enters the compatible shifting stage before the formal prediction. Based on maximizing semantic retention, we implement the domain style matching and shifting through the simple transformation through Fourier transform, which can explicitly and safely shift the target domain back to the source domain whose style is closest to it, requiring no additional model updates and reducing the domain gap. Eventually, the paradigm MSI enters the formal inference stage. The updated target domain is predicted in the main module trained in the previous stage with the benefit of familiar knowledge from the nearest source domain masking scheme. Our paradigm is logically progressive, which can intuitively exclude the confounding influence of domain-specific spurious information along with mitigating domain shifts and implicitly perform semantically invariant representation learning, achieving robust OOD generalization. Extensive experimental results on PACS, VLCS, Office-Home and DomainNet datasets verify the superiority and effectiveness of the proposed method.

DSIL-DDI: A Domain-Invariant Substructure Interaction Learning for Generalizable Drug-Drug Interaction Prediction.

Drug-drug interactions (DDIs) trigger unexpected pharmacological effects in vivo, often with unknown causal mechanisms. Deep learning methods have been developed to better understand DDI. However, learning domain-invariant representations for DDI remains a challenge. Generalizable DDI predictions are closer to reality than source domain predictions. For existing methods, it is difficult to achieve out-of-distribution (OOD) predictions. In this article, focusing on substructure interaction, we propose DSIL-DDI, a pluggable substructure interaction module that can learn domain-invariant representations of DDIs from source domain. We evaluate DSIL-DDI on three scenarios: the transductive setting (all drugs in test set appear in training set), the inductive setting (test set contains new drugs that were not present in training set), and OOD generalization setting (training set and test set belong to two different datasets). The results demonstrate that DSIL-DDI improve the generalization and interpretability of DDI prediction modeling and provides valuable insights for OOD DDI predictions. DSIL-DDI can help doctors ensuring the safety of drug administration and reducing the harm caused by drug abuse.

Causality-inspired Domain Expansion network for single domain generalization

Most existing single domain generalization (SDG) methods focus on extending the distribution of the training data to achieve good generalizability in the target domain by synthesizing out-of-domain data. However, in practice, the generated data are insufficient to cover all possible shifts. When the target distributions are not covered, the spurious associations between irrelevant features and labels captured by a model will deteriorate the generalization performance. To alleviate this problem, in this paper, we first analyze that augmenting the source domain with samples of new styles (e.g., different backgrounds) can mitigate spurious associations between irrelevant features and labels from a causal perspective, which can reduce the interference of non-causal features on the classification labels then propose a novel Causality-inspired Domain Expansion Network (CDEN) for SDG. Specifically, CDEN contains a domain augmentation subnetwork and a representation learning subnetwork. The former uses a special style generator module AdaIN∗ to generate out-of-domain data with the same semantic information but different styles from the source domain data to help the model capture true associations between discriminative features and labels. The latter introduces a novel class-level contrastive learning, instance-level contrastive learning, and invariant risk minimization to help the model further eliminate spurious associations. CDEN progressively generates diverse style data and learns domain invariant representations containing few spurious associations by optimizing the two subnetworks in an adversarial learning manner. We conduct extensive experiments on three benchmark datasets to evaluate the superiority of CDEN, comparing it to fifteen state-of-the-art methods.

EEG-DG: A Multi-Source Domain Generalization Framework for Motor Imagery EEG Classification.

Motor imagery EEG classification plays a crucial role in non-invasive Brain-Computer Interface (BCI) research. However, the performance of classification is affected by the non-stationarity and individual variations of EEG signals. Simply pooling EEG data with different statistical distributions to train a classification model can severely degrade the generalization performance. To address this issue, the existing methods primarily focus on domain adaptation, which requires access to the test data during training. This is unrealistic and impractical in many EEG application scenarios. In this paper, we propose a novel multi-source domain generalization framework called EEG-DG, which leverages multiple source domains with different statistical distributions to build generalizable models on unseen target EEG data. We optimize both the marginal and conditional distributions to ensure the stability of the joint distribution across source domains and extend it to a multi-source domain generalization framework to achieve domain-invariant feature representation, thereby alleviating calibration efforts. Systematic experiments conducted on a simulative dataset, BCI competition IV 2a, 2b, and OpenBMI datasets, demonstrate the superiority and competitive performance of our proposed framework over other state-of-the-art methods. Specifically, EEG-DG achieves average classification accuracies of 81.79% and 87.12% on datasets IV-2a and IV-2b, respectively, and 78.37% and 76.94% for inter-session and inter-subject evaluations on dataset OpenBMI, which even outperforms some domain adaptation methods. Our code is available at https://github.com/zxchit2022/EEG-DG for evaluation.

Towards diverse image-to-image translation via adaptive normalization layer and contrast learning

A nice image-to-image translation framework is able to acquire an explicit and credible mapping relationship between the source domain and target domains while satisfying two requirements. One is simplicity, the other is extensibility over multiple translation tasks. To this end, we design a concise but versatile generative model for image-to-image translation. Our method includes three major ingredients. First, inspired by popular unconditional normalization layers, named Spatially Adaptive Normalization(SPADE). We introduce a novel Semantics-Appearance Spatially Adaptive Normalization (SA-SPADE), taking into account both semantic structure and style appearance. This enables semantic composition and style appearance information to be sufficiently captured and integrated by our normalization layers. Thanks to SA-SPADE, our model extends to multiple image-to-image translation tasks in an unsupervised or supervised way. Second, we carefully designed two symmetrical network branches to provide semantic and appearance information for our normalization layer, namely Semantic Branch (SB) and Appearance Branch(AB) respectively. Third, we propose novel Semantic-aware Contrastive Loss (SCL) and Appearance-aware Contrastive Loss (ACL)based on newly un-/self- supervised contrastive learning. That is, SCL guarantees domain-invariant (e.g., pose, structure) representations between the generated image and the input image, while ACL ensures domain-specific representations (e.g., color, texture) between the generated image and the reference image. As a result, we verify the effectiveness of our method by comparing it with various task-dependent image translation models in both qualitative and quantitative evaluations.

Unsupervised deep domain adaptation algorithm for video based human activity recognition via recurrent neural networks

The integration of cyber-physical systems and artificial intelligent human activity recognition (HAR) applications enables intelligent interactions within a physical environment. In real-world HAR applications, the domain shift between training (source) and testing (target) images captured in different scenarios leads to low classification accuracy. Existing unsupervised domain adaptation (UDA) methods often require some labeled target samples for model adaptation, which limits their practicality. This study proposes a novel unsupervised deep domain adaptation algorithm (UDDAA) for HAR using recurrent neural networks. UDDAA introduces a maximum mean class discrepancy (MMCD) metric, accounting for both inter-class and intra-class differences within each domain. MMCD extends the maximum mean discrepancy to measure the class-level distribution discrepancy across source and target domains, aligning these distributions to enhance domain adaptation performance. Without relying on labeled target data, UDDAA predicts pseudo-labels for the unlabeled target dataset, combining these with labeled source data to train the model on domain-invariant representations. This approach makes UDDAA highly practical for scenarios where labeled target data is difficult or expensive to obtain, enabling human-computer interaction (HCI) systems to function effectively across varied environments and user behaviors. Extensive experiments on benchmark datasets demonstrate UDDAA's superior classification accuracy over existing baselines. Notably, UDDAA achieved 92% and 99% accuracy for University of Central Florida database (UCF) to Human Motion Database (HMDB) and HMDB to UCF transfers, respectively. Additionally, on personal recorded videos with complex backgrounds, it achieved high classification accuracies of 95% for basketball and 90% for football activities, underscoring its generalization ability, robustness, and effectiveness.