Search

Unsupervised domain adaptation person re-identification (UDA Re-ID) aims to leverage the pedestrian knowledge learned from labeled source domain to assist in learning the pedestrian knowledge in the unlabeled target domain. Most of existing investigations typically utilize single-class center clustering algorithms to group unlabeled target domain instances. Unfortunately, single-class center clustering algorithms tend to cluster pedestrian pictures from different identities into the same cluster, leading to inaccurate labels. Training with these noisy labels can undesirably deteriorate the accuracy of UDA Re-ID. Responding to the problem, we propose a multi-class center dynamic contrastive learning (MCC-DCL) for UDA Re-ID, which includes three main parts: multi-center clustering (MCC), dynamic pseudo-labeling (DPL), and dynamic contrastive learning (DCL). In order to reduce noisy labels generated during clustering, we introduce MCC method to generates reliable pseudo-labels for instances. Furthermore, to fully utilize the knowledge learned by the network during each iteration, we propose DPL method to optimizes the pseudo-labels of instances. Finally, for improving the discriminative performance of model and its tolerance to noisy labels, we propose DCL method that utilizes dynamic pseudo-labels and dynamic contrastive loss for supervised training. Comprehensive experiments and analyses demonstrate that MCC-DCL significantly outperforms existing approaches in UDA Re-ID tasks. [ABSTRACT FROM AUTHOR]

The objective of unsupervised domain adaptation (UDA) for person re-identification (re-ID) is to associate person in images captured from heterogeneous camera perspectives. Currently, mainstream UDA methods for person re-ID are mainly conducted in single-source and single-target domain scenarios. Moreover, most of these methods do not take the repercussions of pseudo-label noise on model performance into consideration. Therefore, we put forward an unsupervised multi-source domain adaptation (UMDA) method for person re-ID via feature fusion and pseudo-label refinement. Firstly, our method is designed for scenarios where there exist several source domains and only one target domain. We suggest using feature fusion techniques to minimize the domain disparity among the source domains, and employ pseudo-label refinement techniques to ameliorate the ramifications of label noise on model predictions. To substantiate the effectiveness of the recommended methodology, we carry out a succession of experiments on multiple datasets. The advantage and preeminence of our proposed method can be manifested by the experimental outcomes. [ABSTRACT FROM AUTHOR]

Recently, active domain adaptation (ADA) has become an emerging paradigm, as it significantly boosts the performance of the model with additional supervision. Despite the impressive performance of ADA methods, they are assumed that the source domain can be available during model adaptation. In many scenarios, the source domain can be unavailable due to issues such as data privacy. Consequently, ADA methods fail to achieve the expected results or even become invalid. To solve the problem, we design an effective framework named Feature Mixing and Self-Training (FMAS) for source-free active domain adaptation. Specifically, we adopt Clustering-based Alignment to make the classification boundary clearer to be beneficial to the subsequent sample selection, which can also achieve initial domain adaptation. When reaching active sample selection, we utilize feature mixing to explore the uncertainty and diversity of the sample. We construct the sample candidate pool by Mixup-based Uncertainty Selection and then consider the diversity to overcome the redundancy among the pool by Entropy-based Diversity Selection. Finally, for the remaining unlabeled samples, we adopt the self-training framework, which screens out high-confidence samples to explore the information of unlabeled samples. Thorough experiments show that FMAS improves average accuracy by at least 1 % compared to other methods on benchmark datasets OfficeHome and MiniDomainNet. And FMAS can also achieve better results with ADA methods without the source domain data, which demonstrates FMAS can outperform previous ADA methods. [ABSTRACT FROM AUTHOR]

Source-free unsupervised domain adaptation (SFUDA) seeks to adapt a pre-trained model from the source domain to the unlabeled target domain without using any source domain data. Some existing methods focus on learning transferable representations with only one classifier and cannot exploit full knowledge of the target domain. Therefore, they are unable to obtain a clear classification decision boundary between the source domain and the target domain. Therefore, we propose a Bi-classifier Confidence Score Weighting (BCSW) approach for addressing these issues. We first introduce a novel confidence score for sample weighting adaptation to boost the performance of the target model. Additionally, we exploit the sample mixup strategy to adequately utilize target domain knowledge to form better clusters. We also further design bi-classifier and adopt classifier disparity distance(CDD) to train the target model to effectively push cross-domain distributions close. Experiments show that our method achieves results equal to or better than the most advanced methods on standard benchmarks. [ABSTRACT FROM AUTHOR]

Although the research involving Unsupervised Domain Adaptation (UDA) has been greatly emerging, many proposed UDA algorithms assume that the domain discrepancy is directly minimized. However, this is impractical in practice. Some methods reduce domain discrepancy by obtaining domain invariant and domain private features, but the disadvantage of this approach is that the domain invariant features obtained contain domain private attributes. So we propose a novel UDA algorithm that introduces an adversarial enhancement and gradient discrepancy minimization (AEGDM) to promote domain alignment. Specifically, the AEGDM method, on the one hand, restrains domain private attributes through enhanced adversation losses to reduce the difficulty of overall transfer and improve the degree of domain alignment, on the other hand, it uses gradient feedback signals to update model classifiers. Furthermore, this paper considers that using a classifier trained in the source domain to assign pseudo-labels to target samples may not be accurate enough, so, we adopt a self-supervised clustering algorithm to obtain pseudo-labels of target samples. The average classification accuracy of our method has achieved 89.5% on Office-31, 89.9% on ImageCLEF-DA and 68.8% on Office-Home, which have 3.3%, 0.2% and 1.5% improved to the ETD, respectively. [ABSTRACT FROM AUTHOR]

Source-free unsupervised domain adaptation (SFUDA) uses the knowledge learned from the source domain pre-trained model to perform the task on the target domain without directly accessing the source domain. However, the source domain pre-trained model is biased towards the source domain but deviates from the target domain, so its pseudo-label on the target domain tends to have a large noise. Thus, we should avoid using noisy pseudo-labels to train the model. In this article, we propose a novel kind of source-free unsupervised domain adaptation with maintaining model balance and diversity (SFMBD), which designs a target domain-specific classifier whose classification boundary is far from the high-density area of the target domain feature distribution. In addition, we keep the model balance and promote the model diversity while maintaining its ability to discriminate the target domain. Experimental evaluation of multiple benchmark datasets illustrates the effectiveness of our proposed approach on SFUDA. [ABSTRACT FROM AUTHOR]

Unsupervised Domain Adaptation (UDA) seeks to exploit the source domain knowledge to address similar but unsupervised target domain tasks. To perform UDA, most of the existing works typically learn domain-invariant representations or align the distributions across source and target domains through low-order statistical matching, which fail to explore more discriminative and high-order adaptation information. In this work, we proposed a kind of UDA, namely UDA through high-order tensor matching with discriminative manifold learning (UDA-HOTDML), by exploring the discriminative manifold structure jointly with the high-order tensor to more desirably match cross-domain alignment. In UDA-HOTDML, multiple aspects of domain knowledge are exploited to benefit more generalizable UDA by jointly modeling the discriminative structures of target domain, consistence as well as high-order tensor statistical characteristics. Finally, our evaluation results show that the proposed UDA-HOTDML method outperforms many related UDA methods. [ABSTRACT FROM AUTHOR]

The research involved Unsupervised Domain Adaptation (UDA) has huge emerged. However, almost of them assume that the domain distributions could be transformed into a shared representation space, which does not always hold, making domain-invariant representations challenging to generate directly on the original domains. We propose a novel UDA algorithm introducing a bidirectional generation and middle domains alignment (BGMA) that uses the idea of transmitting middle domains to reduce a cross-domain gap. To explore the middle domains (i.e., fake source/target domain), we embed supervised knowledge in the constructed task network to train a bidirectional generator. Besides, we replace the source and target domains with the generated middle domains, and we reassign the relative influence of each sample to the clusters' centers. Then we specifically design an algorithm to optimize our method with generalization bound analysis and demonstrate its effectiveness through a comprehensive evaluation. [Display omitted] • A novel UDA method via bidirectional generation and middle domains alignment (BGMA) is proposed, which aligns discrepancies between the source and target domains through the constructed middle domains as the surrogate. Considering the classifiers' prediction of fake target domain is the biased estimation. We reasonably reassign the relative effect of each sample to the centers of the clusters. Our method jointly performs transmitting middles, supervised guidance of cross-domain and decision classifier more effectively to reduce the domain gap. • To express the process of BGMA clearly, an optimization algorithm and the generalization error bound for BGMA are constructed. • The effectiveness and superior performance of the BGMA are verified through our extensive ablation studies and evaluations on Office-31, Office-Home and ImageCLEF-DA datasets. [ABSTRACT FROM AUTHOR]