Partial Domain Adaptation (PDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain, where the target label space is a subset of the source label space. In PDA scenario, existing methods typically achieve transferability through distribution alignment in a statistical framework, and discriminability through geometric modeling. These two aspects are often treated as separate frameworks, which severs the intrinsic connection between them. To bridge this gap, we propose a unified framework termed Geometry-aware Conditional Alignment (GCA), which is derived from theoretical insights of Maximum Coding Rate Reduction. GCA collaboratively achieves conditional alignment and orthogonal discriminability in a unified framework, making the learned features more interpretable in both statistical and geometric aspects. As a result, GCA effectively enhances both the transferability and discriminability of features. Extensive experiments on four benchmark datasets validate the effectiveness of GCA.

Diffusion models have achieved impressive generative performance across diverse domains such as image, video, and scientific data generation. However, fine-tuning these models for new tasks remains challenging due to their large scale, architectural diversity, and high sensitivity to hyperparameters—particularly learning rates. In this work, we propose Wasserstein-Aware Transfer (WAT), a principled and effective fine-tuning strategy grounded in diffusion trajectory analysis and optimal transport theory. Our key insight is that the distributional discrepancies between diffusion trajectories from different datasets decrease progressively over time and converge near the noise end. Based on this observation, we introduce a class-wise matching mechanism that minimizes the Wasserstein distance between class distributions of source and target datasets. This enables alignment at the class level without modifying the standard fine-tuning pipeline. To further enhance knowledge retention, we propose a novel sampling strategy that linearly combines class-conditional outputs from both pretrained and fine-tuned models. This method is simple yet effective, requiring negligible computational overhead while preserving domain-specific and generalizable knowledge. Extensive experiments across seven diverse benchmarks demonstrate that WAT reliably enhances generation quality under distribution shifts, outperforming competitive baselines. These results underscore its robustness and affirm the potential of optimal transport as a principled basis for knowledge transfer in diffusion models.

Vision–language models (VLMs) such as CLIP have unlocked powerful zero-shot transfer, yet efficient adaptation to downstream tasks remains challenging. Existing methods often depend on graph structures and dataset-specific tuning, making them sensitive to modality gaps and computationally costly at scale. In this paper, we propose IOTA (Inverse Optimal Transport Adaptation), a lightweight algorithm that reformulates VLMs inference from the perspective of inverse optimal transport (IOT), providing a unified view of training and inference. Under the IOT framework, IOTA enhances zero-shot alignment via a theory-guided unbalanced OT strategy and refines textual prototypes using OT-based pseudo-labels with a marginal-aware adaptive threshold, enabling reliable supervision without gradient updates. The framework naturally extends to few-shot scenarios through a label-guided masking mechanism. By decoupling image–text interactions from other inter-modal dependencies, IOTA avoids task-specific tuning and expensive affinity construction. Extensive experiments on standard benchmarks show that IOTA consistently improves zero-shot and few-shot performance while reducing memory and computation overhead, validating both its theoretical insight and plug-and-play practicality.

Open set domain adaptation (OSDA) aims to transfer classification-oriented knowledge from a labeled source domain to an unlabeled target domain, which faces the challenges from unseen knowledge in open-set scenarios, i.e., unknown classes privileged to the target domain. Existing methods usually identify unknown classes from classifier prediction directly, which are sensitive to the intrinsic clustering structure and cluster numbers of the unknown class data. In this paper, inspired by the sample relation characterization ability of Optimal Transport (OT), we propose a new type of OT method for OSDA, namely, Target-relaxed Optimal Transport (TROT). Compared with existing OT with strict marginal constraints, TROT imposes a single-side relaxation to the mass requirement on the open-set target domain. Theoretically, we prove that such a relaxation can reduce mis-matches between known and unknown classes, which indicates the transport plan of TROT is promising to identify unknown classes. Methodologically, TROT can identify unknown classes adaptively and map the cross-domain shared data with a sparse plan assignment, which improves both the effectiveness and robustness of known class alignment; besides, a graph embedding with multi-cluster structure of unknown classes is designed to learn a discriminative metric space for open-set classification. Empirically, extensive evaluations are conducted on several image datasets, where TROT achieves significant performance improvements compared with existing techniques for visual recognition in open-set scenarios.

Optimal transport (OT) is a rising research area to overcome distribution shifts in real-world data, which has been widely applied in visual signal processing tasks due to its appealing mathematical properties. However, previous works 1) consider the transport cost in Euclidean space, which conflicts with the well-known manifold prior on intrinsic data structure; 2) only consider first-order relation between inputs, which is infeasible for severe shift with heterogeneous spaces. These limitations usually disrupt the manifold structure and degrade the generalization performance on the test data. To deal with these issues, we propose the manifold preserving OT (MPOT) on Gromov-Wasserstein (GW), which introduces 1) the graph-based cost formulation for high-order relation characterization; 2) relation modeling for unshared knowledge between heterogeneous spaces. Mathematically, by encoding the high-order edge information as binary pattern, the GW-based regularization is developed to capture the intrinsic structure for label discriminability. Numerical algorithm with theoretical guarantee is provided, which ensures that MPOT can be efficiently solved by block coordinate descent. Extensive experiments validate MPOT for cross-domain visual classification with changing label spaces.

As an important learning paradigm for signal processing and pattern recognition, unsupervised domain adaptation (UDA), which deals with the learning bias induced by the changing data environments (i.e., domains), has achieved great success in real-world applications. Mainstream UDA methods commonly adopt the discrepancy optimization on the two data domains directly, which ignore the hidden information in the latent intermediate domains and cannot sufficiently learn the invariant knowledge across domains; moreover, they usually fail when the domain gap is significant. In this work, a novel learning principle called Wasserstein invariant risk (WIR) is developed to gradually reduce the bias. The core idea is to recover the latent domains along the Wasserstein geodesic with local structure preservation, and explicitly map them into an invariant space via barycenter mapping. Intuitively, the Wasserstein geodesic captures the non-Euclidean structures of the latent domains. Methodologically, the barycenter mapping along geodesic can: 1) reduce the data discrepancy gradually and explore the hidden information; 2) ensure the consistency of risk estimation across domains; 3) admit invariance property of learning model for changing environments. Extensive experiments on visual UDA classification show the superiority of WIR over SOTA methods.

Aiming to generalize the well-trained gaze estimation model to new target domains, Cross-domain Gaze Estimation (CDGE) is developed for real-world application scenarios. Existing CDGE methods typically extract the domain-invariant features to mitigate domain shift in feature space, which is proved insufficient by Generalized Label Shift (GLS) theory. In this paper, we introduce a novel GLS perspective to CDGE and modelize the cross-domain problem by label and conditional shift problem. A GLS correction framework is presented and a feasible realization is proposed, in which a importance reweighting strategy based on truncated Gaussian distribution is introduced to overcome the continuity challenges in label shift correction. To embed the reweighted source distribution to conditional invariant learning, we further derive a probability-aware estimation of conditional operator discrepancy. Extensive experiments on standard CDGE tasks with different backbone models validate the superior generalization capability across domain and applicability on various models of proposed method.

While data-driven methods such as neural operator have achieved great success in solving differential equations (DEs), they suffer from domain shift problems caused by different learning environments (with data bias or equation changes), which can be alleviated by transfer learning (TL). However, existing TL methods adopted in DEs problems lack either generalizability in general DEs problems or physics preservation during training. In this work, we focus on a general transfer learning method that adaptively correct the domain shift and preserve physical relation within the equation. Mathematically, we characterize the data domain as product distribution and the essential problems as distribution bias and operator bias. A Physics-preserved Optimal Tensor Transport (POTT) method that simultaneously admits generalizability to common DEs and physics preservation of specific problem is proposed to adapt the data-driven model to target domain, utilizing the pushforward distribution induced by the POTT map. Extensive experiments in simulation and real-world datasets demonstrate the superior performance, generalizability and physics preservation of the proposed POTT method.

Partial domain adaptation (PDA) is a challenging task in real-world machine learning scenarios. It aims to transfer knowledge from a labeled source domain to a related unlabeled target domain, where the support set of the source label distribution subsumes the target one. Previous PDA works managed to correct the label distribution shift by weighting samples in the source domain. However, the simple reweighing technique cannot explore the latent structure and sufficiently use the labeled data, and then models are prone to over-fitting on the source domain. In this work, we propose a novel importance sampling-based shift correction (IS2C) method, where new labeled data are sampled from a built sampling domain, whose label distribution is supposed to be the same as the target domain, to characterize the latent structure and enhance the generalization ability of the model. We provide theoretical guarantees for IS2C by proving that the generalization error can be sufficiently dominated by IS2C. In particular, by implementing sampling with the mixture distribution, the extent of shift between source and sampling domains can be connected to generalization error, which provides an interpretable way to build IS2C. To improve knowledge transfer, an optimal transport-based independence criterion is proposed for conditional distribution alignment, where the computation of the criterion can be adjusted to reduce the complexity from $\mathcal {O}(n^{3})$ to $\mathcal {O}(n^{2})$ in realistic PDA scenarios. Extensive experiments on PDA benchmarks validate the theoretical results and demonstrate the effectiveness of our IS2C over existing methods.

Optimal transport (OT) is an important methodology to measure distribution discrepancy, which has achieved promising performance in artificial intelligence applications, e.g., unsupervised domain adaptation. However, from the view of transportation, there are still limitations: 1) the local discriminative structures for downstream tasks, e.g., cluster structure for classification, cannot be explicitly admitted by the learned OT plan; 2) the entropy regularization induces a dense OT plan with increasing uncertainty. To tackle these issues, we propose a novel Probability-Polarized OT (PPOT) framework, which can characterize the structure of OT plan explicitly. Specifically, the probability polarization mechanism is proposed to guide the optimization direction of OT plan, which generates a clear margin between similar and dissimilar transport pairs and reduces the uncertainty. Further, a dynamic mechanism for margin is developed by incorporating task-related information into the polarization, which directly captures the intra/inter class correspondence for knowledge transportation. A mathematical understanding for PPOT is provided from the view of gradient, which ensures interpretability. Extensive experiments on several datasets validate the effectiveness and empirical efficiency of PPOT.

As a crucial step toward real-world learning scenarios with changing environments, dataset shift theory and invariant representation learning algorithm have been extensively studied to relax the identical distribution assumption in classical learning setting. Among the different assumptions on the essential of shifting distributions, generalized label shift (GLS) is the latest developed one which shows great potential to deal with the complex factors within the shift. In this paper, we aim to explore the limitations of current dataset shift theory and algorithm, and further provide new insights by presenting a comprehensive understanding of GLS. From theoretical aspect, two informative generalization bounds are derived, and the GLS learner are proved to be sufficiently close to optimal target model from the Bayesian perspective. The main results show the insufficiency of invariant representation learning, and prove the sufficiency and necessity of GLS correction for generalization, which provide theoretical supports and innovations for exploring generalizable model under dataset shift. From methodological aspect, we provide a unified view of existing shift correction frameworks, and propose a kernel embedding-based correction algorithm (KECA) to minimize the generalization error and achieve successful knowledge transfer. Both theoretical results and extensive experiment evaluations demonstrate the sufficiency and necessity of GLS correction for addressing dataset shift and the superiority of proposed algorithm.

To overcome the restriction of identical distribution assumption, invariant representation learning for unsupervised domain adaptation (UDA) has made significant advances in computer vision and pattern recognition communities. In UDA scenario, the training and test data belong to different domains while the task model is learned to be invariant. Recently, empirical connections between transferability and discriminability have received increasing attention, which is the key to understand the invariant representations. However, theoretical study of these abilities and in-depth analysis of the learned feature structures are unexplored yet. In this work, we systematically analyze the essentials of transferability and discriminability from the geometric perspective. Our theoretical results provide insights into understanding the co-regularization relation and prove the possibility of learning these abilities. From methodology aspect, the abilities are formulated as geometric properties between domain/cluster subspaces (i.e., orthogonality and equivalence) and characterized as the relation between the norms/ranks of multiple matrices. Two optimization-friendly learning principles are derived, which also ensure some intuitive explanations. Moreover, a feasible range for the co-regularization parameters is deduced to balance the learning of geometric structures. Based on the theoretical results, a geometry-oriented model is proposed for enhancing the transferability and discriminability via nuclear norm optimization. Extensive experiment results validate the effectiveness of the proposed model in empirical applications, and verify that the geometric abilities can be sufficiently learned in the derived feasible range.

Domain generalization in semantic segmentation aims to alleviate the performance degradation on unseen domains through learning domain-invariant features. Existing methods diversify images in the source domain by adding complex or even abnormal textures to reduce the sensitivity to domain-specific features. However, these approaches depends heavily on the richness of the texture bank and training them can be time-consuming. In contrast to importing textures arbitrarily or augmenting styles randomly, we focus on the single source domain itself to achieve the generalization. In this paper, we present a novel adaptive texture filtering mechanism to suppress the influence of texture without using augmentation, thus eliminating the interference of domain-specific features. Further, we design a hierarchical guidance generalization network equipped with structure-guided enhancement modules, which purpose to learn the domain-invariant generalized knowledge. Extensive experiments together with ablation studies on widely-used datasets are conducted to verify the effectiveness of the proposed model, and reveal its superiority over other state-of-the-art alternatives.

As an important methodology to measure distribution discrepancy, optimal transport (OT) has been successfully applied to learn generalizable visual models under changing environments. However, there are still limitations, including strict prior assumption and implicit alignment, for current OT modeling in challenging real-world scenarios like partial domain adaptation, where the learned trans-port plan may be biased and negative transfer is inevitable. Thus, it is necessary to explore a more feasible OT methodology for real-world applications. In this work, we focus on the rigorous OT modeling for conditional distribution matching and label shift correction. A novel masked OT (MOT) methodology on conditional distributions is proposed by defining a mask operation with label information. Further, a relaxed and reweighting formulation is proposed to improve the robustness of OT in extreme scenarios. We prove the theoretical equivalence between conditional OT and MOT, which implies the well-defined MOT serves as a computation-friendly proxy. Extensive experiments validate the effectiveness of theoretical results and proposed model.

As a fundamental manner for learning and cognition, transfer learning has attracted widespread attention in recent years. Typical transfer learning tasks include unsupervised domain adaptation (UDA) and few-shot learning (FSL), which both attempt to sufficiently transfer discriminative knowledge from the training environment to the test environment to improve the model's generalization performance. Previous transfer learning methods usually ignore the potential conditional distribution shift between environments. This leads to the discriminability degradation in the test environments. Therefore, how to construct a learnable and interpretable metric to measure and then reduce the gap between conditional distributions is very important in the literature. In this article, we design the Conditional Kernel Bures (CKB) metric for characterizing conditional distribution discrepancy, and derive an empirical estimation with convergence guarantee. CKB provides a statistical and interpretable approach, under the optimal transportation framework, to understand the knowledge transfer mechanism. It is essentially an extension of optimal transportation from the marginal distributions to the conditional distributions. CKB can be used as a plug-and-play module and placed onto the loss layer in deep networks, thus, it plays the bottleneck role in representation learning. From this perspective, the new method with network architecture is abbreviated as BuresNet, and it can be used extract conditional invariant features for both UDA and FSL tasks. BuresNet can be trained in an end-to-end manner. Extensive experiment results on several benchmark datasets validate the effectiveness of BuresNet.

Limited labeled training samples constitute a challenge in hyperspectral image classification, with much research devoted to cross-domain adaptation, where the classes of the source and target domains are different. Current cross-domain few-shot learning methods only use a small number of sample pairs to learn the discriminant features, which limits their performance. To address this problem, we propose a new framework for cross-domain few-shot learning, considering all possible positive and negative pairs in a training batch, and not just pairs between the support and query sets. Furthermore, we propose a new kernel triplet loss to characterize complex nonlinear relationships between samples and design appropriate feature extraction and discriminant networks. Specifically, the source data and target data are simultaneously fed into the same feature extraction network, then the proposed kernel triplet loss on the embedding feature and cross-entropy loss on the softmax output are used to learn discriminant features for both source and target data. Finally, an iterative adversarial strategy is employed to mitigate domain shift between source and target data. The proposed method significantly outperforms state-of-the-art methods in experiments on four target datasets and one source dataset. The code is available at https://github.com/kkcocoon/CFSL-KT.

Learning node representation is a fundamental problem in biological network analysis, as compact representation features reveal complicated network structures and carry useful information for downstream tasks such as link prediction and node classification. Recently, multiple networks that profile objects from different aspects are increasingly accumulated, providing the opportunity to learn objects from multiple perspectives. However, the complex common and specific information across different networks pose challenges to node representation methods. Moreover, ubiquitous noise in networks calls for more robust representation. To deal with these problems, we present a representation learning method for multiple biological networks. First, we accommodate the noise and spurious edges in networks using denoised diffusion, providing robust connectivity structures for the subsequent representation learning. Then, we introduce a graph regularized integration model to combine refined networks and compute common representation features. By using the regularized decomposition technique, the proposed model can effectively preserve the common structural property of different networks and simultaneously accommodate their specific information, leading to a consistent representation. A simulation study shows the superiority of the proposed method on different levels of noisy networks. Three network-based inference tasks, including drug-target interaction prediction, gene function identification and fine-grained species categorization, are conducted using representation features learned from our method. Biological networks at different scales and levels of sparsity are involved. Experimental results on real-world data show that the proposed method has robust performance compared with alternatives. Overall, by eliminating noise and integrating effectively, the proposed method is able to learn useful representations from multiple biological networks.

Unsupervised domain adaptation is effective in leveraging rich information from a labeled source domain to an unlabeled target domain. Though deep learning and adversarial strategy made a significant breakthrough in the adaptability of features, there are two issues to be further studied. First, hard-assigned pseudo labels on the target domain are arbitrary and error-prone, and direct application of them may destroy the intrinsic data structure. Second, batch-wise training of deep learning limits the characterization of the global structure. In this paper, a Riemannian manifold learning framework is proposed to achieve transferability and discriminability simultaneously. For the first issue, this framework establishes a probabilistic discriminant criterion on the target domain via soft labels. Based on pre-built prototypes, this criterion is extended to a global approximation scheme for the second issue. Manifold metric alignment is adopted to be compatible with the embedding space. The theoretical error bounds of different alignment metrics are derived for constructive guidance. The proposed method can be used to tackle a series of variants of domain adaptation problems, including both vanilla and partial settings. Extensive experiments have been conducted to investigate the method and a comparative study shows the superiority of the discriminative manifold learning framework.

For a broad range of applications, hyperspectral image (HSI) classification is a hot topic in remote sensing, and convolutional neural network (CNN)-based methods are drawing increasing attention. However, to train millions of parameters in CNN requires a large number of labeled training samples, which are difficult to collect. A conventional Gabor filter can effectively extract spatial information with different scales and orientations without training, but it may be missing some important discriminative information. In this article, we propose the Gabor ensemble filter (GEF), a new convolutional filter to extract deep features for HSI with fewer trainable parameters. GEF filters each input channel by some fixed Gabor filters and learnable filters simultaneously, then reduces the dimensions by some learnable 1×1 filters to generate the output channels. The fixed Gabor filters can extract common features with different scales and orientations, while the learnable filters can learn some complementary features that Gabor filters cannot extract. Based on GEF, we design a network architecture for HSI classification, which extracts deep features and can learn from limited training samples. In order to simultaneously learn more discriminative features and an end-to-end system, we propose to introduce the local discriminant structure for cross-entropy loss by combining the triplet hard loss. Results of experiments on three HSI datasets show that the proposed method has significantly higher classification accuracy than other state-of-the-art methods. Moreover, the proposed method is speedy for both training and testing.

Multi-source domain adaptation (MDA) aims to transfer knowledge from multiple source domains to an unlabeled target domain. MDA is a challenging task due to the severe domain shift, which not only exists between target and source but also exists among diverse sources. Prior studies on MDA either estimate a mixed distribution of source domains or combine multiple single-source models, but few of them delve into the relevant information among diverse source domains. For this reason, we propose a novel MDA approach, termed Pseudo Target for MDA (PTMDA). Specifically, PTMDA maps each group of source and target domains into a group-specific subspace using adversarial learning with a metric constraint, and constructs a series of pseudo target domains correspondingly. Then we align the remainder source domains with the pseudo target domain in the subspace efficiently, which allows to exploit additional structured source information through the training on pseudo target domain and improves the performance on the real target domain. Besides, to improve the transferability of deep neural networks (DNNs), we replace the traditional batch normalization layer with an effective matching normalization layer, which enforces alignments in latent layers of DNNs and thus gains further promotion. We give theoretical analysis showing that PTMDA as a whole can reduce the target error bound and leads to a better approximation of the target risk in MDA settings. Extensive experiments demonstrate PTMDA's effectiveness on MDA tasks, as it outperforms state-of-the-art methods in most experimental settings.

Early and accurate severity assessment of Coronavirus disease 2019 (COVID-19) based on computed tomography (CT) images offers a great help to the estimation of intensive care unit event and the clinical decision of treatment planning. To augment the labeled data and improve the generalization ability of the classification model, it is necessary to aggregate data from multiple sites. This task faces several challenges including class imbalance between mild and severe infections, domain distribution discrepancy between sites, and presence of heterogeneous features. In this paper, we propose a novel domain adaptation (DA) method with two components to address these problems. The first component is a stochastic class-balanced boosting sampling strategy that overcomes the imbalanced learning problem and improves the classification performance on poorly-predicted classes. The second component is a representation learning that guarantees three properties: 1) domain-transferability by prototype triplet loss, 2) discriminant by conditional maximum mean discrepancy loss, and 3) completeness by multi-view reconstruction loss. Particularly, we propose a domain translator and align the heterogeneous data to the estimated class prototypes (i.e., class centers) in a hyper-sphere manifold. Experiments on cross-site severity assessment of COVID-19 from CT images show that the proposed method can effectively tackle the imbalanced learning problem and outperform recent DA approaches.

As a vital problem in classification-oriented transfer, unsupervised domain adaptation (UDA) has attracted widespread attention in recent years. Previous UDA methods assume the marginal distributions of different domains are shifted while ignoring the discriminant information in the label distributions. This leads to classification performance degeneration in real applications. In this work, we focus on the conditional distribution shift problem which is of great concern to current conditional invariant models. We aim to seek a kernel covariance embedding for conditional distribution which remains yet unexplored. Theoretically, we propose the Conditional Kernel Bures (CKB) metric for characterizing conditional distribution discrepancy, and derive an empirical estimation for the CKB metric without introducing the implicit kernel feature map. It provides an interpretable approach to understand the knowledge transfer mechanism. The established consistency theory of the empirical estimation provides a theoretical guarantee for convergence. A conditional distribution matching network is proposed to learn the conditional invariant and discriminative features for UDA. Extensive experiments and analysis show the superiority of our proposed model.

Domain adaptation (DA) and transfer learning with statistical property description is very important in image analysis and data classification. This article studies the domain adaptive feature representation problem for the heterogeneous data, of which both the feature dimensions and the sample distributions across domains are so different that their features cannot be matched directly. To transfer the discriminant information efficiently from the source domain to the target domain, and then enhance the classification performance for the target data, we first introduce two projection matrices specified for different domains to transform the heterogeneous features into a shared space. We then propose a joint kernel regression model to learn the regression variable, which is called feature translator in this article. The novelty focuses on the exploration of optimal experimental design (OED) to deal with the heterogeneous and nonlinear DA by seeking the covariance structured feature translators (CSFTs). An approximate and efficient method is proposed to compute the optimal data projections. Comprehensive experiments are conducted to validate the effectiveness and efficacy of the proposed model. The results show the state-of-the-art performance of our method in heterogeneous DA.

Conditional maximum mean discrepancy (CMMD) can capture the discrepancy between conditional distributions by drawing support from nonlinear kernel functions; thus, it has been successfully used for pattern classification. However, CMMD does not work well on complex distributions, especially when the kernel function fails to correctly characterize the difference between intraclass similarity and interclass similarity. In this paper, a new kernel learning method is proposed to improve the discrimination performance of CMMD. It can be operated with deep network features iteratively and thus denoted as KLN for abbreviation. The CMMD loss and an autoencoder (AE) are used to learn an injective function. By considering the compound kernel, that is, the injective function with a characteristic kernel, the effectiveness of CMMD for data category description is enhanced. KLN can simultaneously learn a more expressive kernel and label prediction distribution; thus, it can be used to improve the classification performance in both supervised and semisupervised learning scenarios. In particular, the kernel-based similarities are iteratively learned on the deep network features, and the algorithm can be implemented in an end-to-end manner. Extensive experiments are conducted on four benchmark datasets, including MNIST, SVHN, CIFAR-10, and CIFAR-100. The results indicate that KLN achieves the state-of-the-art classification performance.

Unsupervised domain adaptation (UDA) aims at reducing the distribution discrepancy when transferring knowledge from a labeled source domain to an unlabeled target domain. Previous UDA methods assume that the source and target domains share an identical label space, which is unrealistic in practice since the label information of the target domain is agnostic. This article focuses on a more realistic UDA scenario, i.e., partial domain adaptation (PDA), where the target label space is subsumed to the source label space. In the PDA scenario, the source outliers that are absent in the target domain may be wrongly matched to the target domain (technically named negative transfer), leading to performance degradation of UDA methods. This article proposes a novel target-domain-specific classifier learning-based domain adaptation (TSCDA) method. TSCDA presents a soft-weighed maximum mean discrepancy criterion to partially align feature distributions and alleviate negative transfer. Also, it learns a target-specific classifier for the target domain with pseudolabels and multiple auxiliary classifiers to further address the classifier shift. A module named peers-assisted learning is used to minimize the prediction difference between multiple target-specific classifiers, which makes the classifiers more discriminant for the target domain. Extensive experiments conducted on three PDA benchmark data sets show that TSCDA outperforms other state-of-the-art methods with a large margin, e.g., 4% and 5.6% averagely on Office-31 and Office-Home, respectively.

Unsupervised domain adaptation is effective in leveraging the rich information from the source domain to the unsupervised target domain. Though deep learning and adversarial strategy make an important breakthrough in the adaptability of features, there are two issues to be further explored. First, the hard-assigned pseudo labels on the target domain are risky to the intrinsic data structure. Second, the batch-wise training manner in deep learning limits the description of the global structure. In this paper, a Riemannian manifold learning framework is proposed to achieve transferability and discriminability consistently. As to the first problem, this method establishes a probabilistic discriminant criterion on the target domain via soft labels. Further, this criterion is extended to a global approximation scheme for the second issue; such approximation is also memory-saving. The manifold metric alignment is exploited to be compatible with the embedding space. A theoretical error bound is derived to facilitate the alignment. Extensive experiments have been conducted to investigate the proposal and results of the comparison study manifest the superiority of consistent manifold learning framework.

Unsupervised domain adaptation (UDA) is a representative problem in transfer learning, which aims to improve the classification performance on an unlabeled target domain by exploiting discriminant information from a labeled source domain. The optimal transport model has been used for UDA in the perspective of distribution matching. However, the transport distance cannot reflect the discriminant information from either domain knowledge or category prior. In this work, we propose an enhanced transport distance (ETD) for UDA. This method builds an attention-aware transport distance, which can be viewed as the prediction feedback of the iteratively learned classifier, to measure the domain discrepancy. Further, the Kantorovich potential variable is re-parameterized by deep neural networks to learn the distribution in the latent space. The entropy-based regularization is developed to explore the intrinsic structure of the target domain. The proposed method is optimized alternately in an end-to-end manner. Extensive experiments are conducted on four benchmark datasets to demonstrate the SOTA performance of ETD.

Learning domain adaptive features aims to enhance the classification performance of the target domain by exploring the discriminant information from an auxiliary source set. Let X denote the feature and Y as the label. The most typical problem to be addressed is that PXYhas a so large variation between different domains that classification in the target domain is difficult. In this paper, we study the generalized conditional domain adaptation (DA) problem, in which both PYand PX|Ychange across domains, in a causal perspective. We propose transforming the class conditional probability matching to the marginal probability matching problem, under a proper assumption. We build an intermediate domain by employing a regression model. In order to enforce the most relevant data to reconstruct the intermediate representations, a low-rank constraint is placed on the regression model for regularization. The low-rank constraint underlines a global algebraic structure between different domains, and stresses the group compactness in representing the samples. The new model is considered under the discriminant subspace framework, which is favorable in simultaneously extracting the classification information from the source domain and adaptation information across domains. The model can be solved by an alternative optimization manner of quadratic programming and the alternative Lagrange multiplier method. To the best of our knowledge, this paper is the first to exploit low-rank representation, from the source domain to the intermediate domain, to learn the domain adaptive features. Comprehensive experimental results validate that the proposed method provides better classification accuracies with DA, compared with well-established baselines.

Unsupervised domain adaptation in person re-identification resorts to labeled source data to promote the model training on target domain, facing the dilemmas caused by large domain shift and large camera variations. The non-overlapping labels challenge that the source domain and the target domain have entirely different persons further increases the re-identification difficulty. In this paper, we propose a novel algorithm to narrow such domain gaps. We derive a camera style adaptation framework to learn the style-based mappings between different camera views, from the target domain to the source domain, and then we can transfer the identity-based distribution from the source domain to the target domain on the camera level. Target camera variations can be captured by the style adaptation method, thus, the re-identification model trained on the target domain can learn target camera-invariant features better. It indicates that the style translator approximates an appropriate metric space for improving feature matching. To overcome the non-overlapping labels challenge and guide the person re-identification model to narrow the gap further, an efficient and effective soft-labeling method is proposed to mine the intrinsic local structure of the target domain through building the connection between GAN-translated source domain and the target domain. Experiment results conducted on real benchmark datasets indicate that our method gets state-of-the-art results.

Image set recognition has been widely applied in many practical problems like real-time video retrieval and image caption tasks. Due to its superior performance, it has grown into a significant topic in recent years. However, images with complicated variations, e.g., postures and human ages, are difficult to address, as these variations are continuous and gradual with respect to image appearance. Consequently, the crucial point of image set recognition is to mine the intrinsic connection or structural information from the image batches with variations. In this work, a Discriminant Residual Analysis (DRA) method is proposed to improve the classification performance by discovering discriminant features in related and unrelated groups. Specifically, DRA attempts to obtain a powerful projection which casts the residual representations into a discriminant subspace. Such a projection subspace is expected to magnify the useful information of the input space as much as possible, then the relation between the training set and the test set described by the given metric or distance will be more precise in the discriminant subspace. We also propose a nonfeasance strategy by defining another approach to construct the unrelated groups, which help to reduce furthermore the cost of sampling errors. Two regularization approaches are used to deal with the probable small sample size problem. Extensive experiments are conducted on benchmark databases, and the results show superiority and efficiency of the new methods.

As a powerful approach for exploratory data analysis, unsupervised clustering is a fundamental task in computer vision and pattern recognition. Many clustering algorithms have been developed, but most of them perform unsatisfactorily on the data with complex structures. Recently, adversarial autoencoder (AE) (AAE) shows effectiveness on tackling such data by combining AE and adversarial training, but it cannot effectively extract classification information from the unlabeled data. In this brief, we propose dual AAE (Dual-AAE) which simultaneously maximizes the likelihood function and mutual information between observed examples and a subset of latent variables. By performing variational inference on the objective function of Dual-AAE, we derive a new reconstruction loss which can be optimized by training a pair of AEs. Moreover, to avoid mode collapse, we introduce the clustering regularization term for the category variable. Experiments on four benchmarks show that Dual-AAE achieves superior performance over state-of-the-art clustering methods. In addition, by adding a reject option, the clustering accuracy of Dual-AAE can reach that of supervised CNN algorithms. Dual-AAE can also be used for disentangling style and content of images without using supervised information.

Local feature descriptor plays a key role in different image classification applications. Some of these methods such as local binary pattern and image gradient orientations have been proven effective to some extent. However, such traditional descriptors which only utilize single-type features, are deficient to capture the edges and orientations information and intrinsic structure information of images. In this paper, we propose a kernel embedding multiorientation local pattern (MOLP) to address this problem. For a given image, it is first transformed by gradient operators in local regions, which generate multiorientation gradient images containing edges and orientations information of different directions. Then the histogram feature which takes into account the sign component and magnitude component, is extracted to form the refined feature from each orientation gradient image. The refined feature captures more information of the intrinsic structure, and is effective for image representation and classification. Finally, the multiorientation refined features are automatically fused in the kernel embedding discriminant subspace learning model. The extensive experiments on various image classification tasks, such as face recognition, texture classification, object categorization, and palmprint recognition show that MOLP could achieve competitive performance with those state-of-the art methods.

We propose a novel linear learning system based on the peak price tracking (PPT) strategy for portfolio selection (PS). Recently, the topic of tracking control attracts intensive attention and some novel models are proposed based on backstepping methods, such that the system output tracks a desired trajectory. The proposed system has a similar evolution with a transform function that aggressively tracks the increasing power of different assets. As a result, the better performing assets will receive more investment. The proposed PPT objective can be formulated as a fast backpropagation algorithm, which is suitable for large-scale and time-limited applications, such as high-frequency trading. Extensive experiments on several benchmark data sets from diverse real financial markets show that PPT outperforms other state-of-the-art systems in computational time, cumulative wealth, and risk-adjusted metrics. It suggests that PPT is effective and even more robust than some defensive systems in PS.

We propose a set of novel radial basis functions with adaptive input and composite trend representation (AICTR) for portfolio selection (PS). Trend representation of asset price is one of the main information to be exploited in PS. However, most state-of-the-art trend representation-based systems exploit only one kind of trend information and lack effective mechanisms to construct a composite trend representation. The proposed system exploits a set of RBFs with multiple trend representations, which improves the effectiveness and robustness in price prediction. Moreover, the input of the RBFs automatically switches to the best trend representation according to the recent investing performance of different price predictions. We also propose a novel objective to combine these RBFs and select the portfolio. Extensive experiments on six benchmark data sets (including a new challenging data set that we propose) from different real-world stock markets indicate that the proposed RBFs effectively combine different trend representations and AICTR achieves state-of-the-art investing performance and risk control. Besides, AICTR withstands the reasonable transaction costs and runs fast; hence, it is applicable to real-world financial environments.

Dimension reduction is an important topic in pattern analysis and machine learning, and it has wide applications in feature representation and pattern classification. In the past two decades, sliced inverse regression (SIR) has attracted much research efforts due to its effectiveness and efficacy in dimension reduction. However, two drawbacks limit further applications of SIR. First, the computation complexity of SIR is usually high in the situation of high-dimensional data. Second, sparsity of projection subspace is not well mined for improving the feature selection and model interpretation abilities. This paper proposes to compute the SIR projection vectors in the spectral space, then an approximated regression solution can be obtained with a faster speed. Moreover, the adaptive lasso is used to attain a sparse and globally optimal solution, which is important in variable selection. To complete the robust pattern classification task with corruptions, a correntropy-based and class-wise regression model is designed in this paper. It takes a smooth penalty instead of sparsity constraint in the regression coefficients, and it can be conducted in class-wise, thus it is more flexible in practice. Extensive experiments are conducted by using some real and benchmark data sets, e.g., high-dimensional facial images and gene microarray data, to evaluate the new algorithms. The new proposals attain competitive results and are compared with other state-of-the-art methods.

A sparse representation classifier (SRC) and a kernel discriminant analysis (KDA) are two successful methods for face recognition. An SRC is good at dealing with occlusion, while a KDA does well in suppressing intraclass variations. In this paper, we propose kernel extended dictionary (KED) for face recognition, which provides an efficient way for combining KDA and SRC. We first learn several kernel principal components of occlusion variations as an occlusion model, which can represent the possible occlusion variations efficiently. Then, the occlusion model is projected by KDA to get the KED, which can be computed via the same kernel trick as new testing samples. Finally, we use structured SRC for classification, which is fast as only a small number of atoms are appended to the basic dictionary, and the feature dimension is low. We also extend KED to multikernel space to fuse different types of features at kernel level. Experiments are done on several large-scale data sets, demonstrating that not only does KED get impressive results for nonoccluded samples, but it also handles the occlusion well without overfitting, even with a single gallery sample per subject.

Robust descriptor-based subspace learning with complex data is an active topic in pattern analysis and machine intelligence. A few researches concentrate the optimal design on feature representation and metric learning. However, traditionally used features of single-type, e.g., image gradient orientations (IGOs), are deficient to characterize the complete variations in robust and discriminant subspace learning. Meanwhile, discontinuity in edge alignment and feature match are not been carefully treated in the literature. In this paper, local order constrained IGOs are exploited to generate robust features. As the difference-based filters explicitly consider the local contrasts within neighboring pixel points, the proposed features enhance the local textures and the order-based coding ability, thus discover intrinsic structure of facial images further. The multimodal features are automatically fused in the most discriminant subspace. The utilization of adaptive interaction function suppresses outliers in each dimension for robust similarity measurement and discriminant analysis. The sparsity-driven regression model is modified to adapt the classification issue of the compact feature representation. Extensive experiments are conducted by using some benchmark face data sets, e.g., of controlled and uncontrolled environments, to evaluate our new algorithm.

In this paper, we propose a novel discriminative and compact coding (DCC) for robust face recognition. It introduces multiple error measurements into regression model. They collaborate to tune regression codes of different properties (sparsity, compactness, high discriminating ability, etc.), to further improve robustness and adaptivity of the regression model. We propose two types of coding models: 1) multiscale error measurements that produces sparse and highly discriminative codes and 2) inspires within-class collaborative representation that produces sparse and compact codes. The update of codes and the combination of different errors are automatically processed. DCC is also robust to the choice of parameters, producing stable regression residuals which are crucial to classification. Extensive experiments on benchmark datasets show that DCC has promising performance and outperforms other state-of-the-art regression models.

Lambertian model is a classical illumination model consisting of a surface albedo component and a light intensity component. Some previous researches assume that the light intensity component mainly lies in the large-scale features. They adopt holistic image decompositions to separate it out, but it is difficult to decide the separating point between large-scale and small-scale features. In this paper, we propose to take a logarithm transform, which can change the multiplication of surface albedo and light intensity into an additive model. Then, a difference (substraction) between two pixels in a neighborhood can eliminate most of the light intensity component. By dividing a neighborhood into subregions, edgemaps of multiple scales can be obtained. Then, each edgemap is multiplied by a weight that can be determined by an independent training scheme. Finally, all the weighted edgemaps are combined to form a robust holistic feature map. Extensive experiments on four benchmark data sets in controlled and uncontrolled lighting conditions show that the proposed method has promising results, especially in uncontrolled lighting conditions, even mixed with other complicated variations.

As the data acquirement technologies develop rapidly, both the amount and types of data become larger and larger. However, noise and outliers usually attach to the data and then affect the real performance of leaning algorithms in data mining and pattern analysis. To address this problem, the importance of the sample itself in building the optimal subspace is explored, and then an importance-sampling-inspired method is proposed for outlier suppressing feature extraction. First, we assign each sample a weight, which is estimated by graph Laplacian, and then calculate the approximated mean for each subject. By highlighting the most subject-oriented samples, the weighted average and the scatter metrics can be measured with maximum margins and superior classification performance. The supervised information integrates local data structure with respective contributions to building the optimal subspace. The linear criterion can be extended to a nonlinear case by the kernel trick. A regularization framework is proposed to deal with the rank-deficient problem, which is usually induced by the small sample size of training set. Competitive performance of our algorithm has been validated by extensive experiments performed on the synthetic and benchmark data, including facial images and gene micro-array data.

In this paper, we propose a multilayer surface albedo (MLSA) model to tackle face recognition in bad lighting conditions, especially with reference images in bad lighting conditions. Some previous researches conclude that illumination variations mainly lie in the large-scale features of an image and extract small-scale features in the surface albedo (or surface texture). However, this surface albedo is not robust enough, which still contains some detrimental sharp features. To improve robustness of the surface albedo, MLSA further decomposes it as a linear sum of several detailed layers, to separate and represent features of different scales in a more specific way. Then, the layers are adjusted by separate weights, which are global parameters and selected for only once. A criterion function is developed to select these layer weights with an independent training set. Despite controlled illumination variations, MLSA is also effective to uncontrolled illumination variations, even mixed with other complicated variations (expression, pose, occlusion, and so on). Extensive experiments on four benchmark data sets show that MLSA has good receiver operating characteristic curve and statistical discriminating capability. The refined albedo improves recognition performance, especially with reference images in bad lighting conditions.

Face recognition under uncontrolled conditions, e.g., complex backgrounds and variable resolutions, is still challenging in image processing and computer vision. Although many methods have been proved well-performed in the controlled settings, they are usually of weak generality across different data sets. Meanwhile, several properties of the source domain, such as background and the size of subjects, play an important role in determining the final classification results. A transferrable representation learning model is proposed in this paper to enhance the recognition performance. To deeply exploit the discriminant information from the source domain and the target domain, the bioinspired face representation is modeled as structured and approximately stable characterization for the commonality between different domains. The method outputs a grouped boost of the features, and presents a reasonable manner for highlighting and sharing discriminant orientations and scales. Notice that the method can be viewed as a framework, since other feature generation operators and classification metrics can be embedded therein, and then, it can be applied to more general problems, such as low-resolution face recognition, object detection and categorization, and so forth. Experiments on the benchmark databases, including uncontrolled Face Recognition Grand Challenge v2.0 and Labeled Faces in the Wild show the efficacy of the proposed transfer learning algorithm.

Face recognition with illumination or pose variation is a challenging problem in image processing and pattern recognition. A novel algorithm using band-reweighed Gabor kernel embedding to deal with the problem is proposed in this paper. For a given image, it is first transformed by a group of Gabor filters, which output Gabor features using different orientation and scale parameters. Fisher scoring function is used to measure the importance of features in each band, and then, the features with the largest scores are preserved for saving memory requirements. The reduced bands are combined by a vector, which is determined by a weighted kernel discriminant criterion and solved by a constrained quadratic programming method, and then, the weighted sum of these nonlinear bands is defined as the similarity between two images. Compared with existing concatenation-based Gabor feature representation and the uniformly weighted similarity calculation approaches, our method provides a new way to use Gabor features for face recognition and presents a reasonable interpretation for highlighting discriminant orientations and scales. The minimum Mahalanobis distance considering the spatial correlations within the data is exploited for feature matching, and the graphical lasso is used therein for directly estimating the sparse inverse covariance matrix. Experiments using benchmark databases show that our new algorithm improves the recognition results and obtains competitive performance.

Face recognition with occlusion is common in the real world. Inspired by the works of structured sparse representation, we try to explore the structure of the error incurred by occlusion from two aspects: the error morphology and the error distribution. Since human beings recognize the occlusion mainly according to its region shape or profile without knowing accurately what the occlusion is, we argue that the shape of the occlusion is also an important feature. We propose a morphological graph model to describe the morphological structure of the error. Due to the uncertainty of the occlusion, the distribution of the error incurred by occlusion is also uncertain. However, we observe that the unoccluded part and the occluded part of the error measured by the correntropy induced metric follow the exponential distribution, respectively. Incorporating the two aspects of the error structure, we propose the structured sparse error coding for face recognition with occlusion. Our extensive experiments demonstrate that the proposed method is more stable and has higher breakdown point in dealing with the occlusion problems in face recognition as compared to the related state-of-the-art methods, especially for the extreme situation, such as the high level occlusion and the low feature dimension.

Practical video scene and face recognition systems are sometimes confronted with low-resolution (LR) images. The faces may be very small even if the video is clear, thus it is difficult to directly measure the similarity between the faces and the high-resolution (HR) training samples. Traditional super-resolution (SR) methods based face recognition usually have limited performance because the target of SR may not be consistent with that of classification, and time-consuming SR algorithms are not suitable for real-time applications. In this paper, a new feature extraction method called Coupled Kernel Embedding (CKE) is proposed for LR face recognition without any SR preprocessing. In this method, the final kernel matrix is constructed by concatenating two individual kernel matrices in the diagonal direction, and the (semi-)positively definite properties are preserved for optimization. CKE addresses the problem of comparing multi-modal data that are difficult for conventional methods in practice due to the lack of an efficient similarity measure. Particularly, different kernel types (e.g., linear, Gaussian, polynomial) can be integrated into an uniformed optimization objective, which cannot be achieved by simple linear methods. CKE solves this problem by minimizing the dissimilarities captured by their kernel Gram matrices in the low- and high-resolution spaces. In the implementation, the nonlinear objective function is minimized by a generalized eigenvalue decomposition. Experiments on benchmark and real databases show that our CKE method indeed improves the recognition performance.