Dual contrastive universal adaptation network for multi-source visual recognition

Multisource unsupervised domain adaptation (MUDA) is an important and challenging topic for target classification with the assistance of labeled data in source domains. When we have several labeled source domains, it is difficult to map all source domains and target domain into a common feature space for classifying the targets well. In this article, a new progressive multisource domain adaptation network (PMSDAN) is proposed to further improve the classification performance. PMSDAN mainly consists of two steps for distribution alignment. First, the multiple source domains are integrated as one auxiliary domain to match the distribution with the target domain. By doing this, we can generally reduce the distribution discrepancy between each source and target domains, as well as the discrepancy between different source domains. It can efficiently explore useful knowledge from the integrated source domain. Second, to mine assistance knowledge from each source domain as much as possible, the distribution of the target domain is separately aligned with that of each source domain. A weighted fusion method is employed to combine the multiple classification results for making the final decision. In the optimization of domain adaption, weighted hybrid maximum mean discrepancy (WHMMD) is proposed, and it considers both the interclass and intraclass discrepancies. The effectiveness of the proposed PMSDAN is demonstrated in the experiments comparing with some state-of-the-art methods.

Unsupervised domain adaptation aims to transfer knowledge from labeled source domain to unlabeled target domain. Recently, multisource domain adaptation (MDA) has begun to attract attention. Its performance should go beyond simply mixing all source domains together for knowledge transfer. In this article, we propose a novel prototype-based method for MDA. Specifically, for solving the problem that the target domain has no label, we use the prototype to transfer the semantic category information from source domains to target domain. First, a feature extraction network is applied to both source and target domains to obtain the extracted features from which the domain-invariant features and domain-specific features will be disentangled. Then, based on these two kinds of features, the named inherent class prototypes and domain prototypes are estimated, respectively. Then a prototype mapping to the extracted feature space is learned in the feature reconstruction process. Thus, the class prototypes for all source and target domains can be constructed in the extracted feature space based on the previous domain prototypes and inherent class prototypes. By forcing the extracted features are close to the corresponding class prototypes for all domains, the feature extraction network is progressively adjusted. In the end, the inherent class prototypes are used as a classifier in the target domain. Our contribution is that through the inherent class prototypes and domain prototypes, the semantic category information from source domains is transformed into the target domain by constructing the corresponding class prototypes. In our method, all source and target domains are aligned twice at the feature level for better domain-invariant features and more closer features to the class prototypes, respectively. Several experiments on public data sets also prove the effectiveness of our method.

Multi-source Domain Adaptation (MSDA) is more practical but challenging than the conventional unsupervised domain adaptation due to the involvement of diverse multiple data sources. Two fundamental challenges of MSDA are: (i) how to deal with the diversity in the multiple source domains and (ii) how to cope with the data shift between the target domain and the source domains. In this paper, to address the first challenge, we propose a theoretical-guaranteed approach to combine domain experts locally trained on its own source domain to achieve a combined multi-source teacher that globally predicts well on the mixture of source domains. To address the second challenge, we propose to bridge the gap between the target domain and the mixture of source domains in the latent space via a generator or feature extractor. Together with bridging the gap in the latent space, we train a student to mimic the predictions of the teacher expert on both source and target examples. In addition, our approach is guaranteed with rigorous theory offered insightful justifications of how each component influences the transferring performance. Extensive experiments conducted on three benchmark datasets show that our proposed method achieves state-of-the-art performances to the best of our knowledge.

Domain consistency regularization for unsupervised multi-source domain adaptive classification

Intelligent fault diagnosis methods based on domain adaptation (DA) have been extensively employed for tackling domain shift problems, and the basic diagnosis tasks under time-varying working conditions were well achieved. Nevertheless, the existing methods usually focus on learning diagnosis knowledge from single-source domain while ignoring abundant underlying information in multisource domain. In practical scenarios, multiple source domains are available, and there are few studies in fault diagnosis based on multisource DA. To this end, a novel multisource domain feature adaptation network (MDFAN) is proposed for bearing fault diagnosis under time-varying working conditions. The proposed network first uses a feature extractor to learn transferable features from different pairs of source and target domains, and then, a domain-specific distribution alignment module is constructed, which adopts the intra-domain alignment strategy and the inter-domain alignment strategy to reduce the shift between all domain pairs. Meanwhile, considering the classifier prediction disagreement, a classifier alignment module is further designed to relieve the classifier prediction discrepancy and enhance the prediction consistency. Case studies on two real datasets with multiple sources demonstrate the effectiveness of the proposed network, and the comparison results show its robustness and superiority.

Multi-source domain adaptation leverages complementary knowledge from multiple source domains to enhance transfer effectiveness, making it more suitable for complex medical scenarios compared to single-source domain adaptation. However, most existing studies operate under the assumption that the source and target domains share identical class distributions, leaving the challenge of addressing class shift in multi-source domain adaptation largely unexplored. To address this gap, this study proposes a Class-Aware Multi-Source Domain Adaptation algorithm based on a Reweighted Matrix Matching strategy (CAMSDA-RMM). This algorithm employs a class-aware strategy to strengthen positive transfer effects between similar classes. Additionally, first-order and second-order moment matching strategies are applied to effectively align the source and target domains, while an adaptive weighting mechanism is utilized to optimize the contributions of different source domains to the target domain. These approaches collectively improve classification accuracy and domain adaptability. Experimental results on four publicly available chest X-ray datasets demonstrate that the superiority of the proposed method.

Regular domain adaptation (DA) problems are interested in source examples drawn from a single source distribution, yet they probably come from multiple source domains in reality. Compared with DAs, Multi-Source DA (MSDA) is more challenging to settle: The extra domain shifts exist between source domains and moreover, the multi-source domains may also disagree on their semantic information. In this section, we surveyed Deep CockTail Network (DCTN), a prevalent MSDA algorithm that battles the multi-source-derived domain and semantic shifts. The ideology behind is inspired by making cocktails with multiple kinds of stuff (i.e. sources in our background). In particular, DCTN replays two alternating learning phases: (1) DCTN goes through a multi-way adversarial DA process to minimize the domain discrepancy between the target and each source, in order to obtain domain-invariant features. In this process, each target example would lead to the source-specific perplexity scores, denoting how similar each target feature appears to a feature from one of the source domains. (2) Integrated with the perplexity scores, the multi-source category classifiers categorizes target samples, and the pseudo-labeled target samples and source samples jointly update the category classifiers and the feature extractor. In the empirical studies, DCTNs are evaluated in three domain adaptation benchmarks in vanilla and source-category-shift MSDA scenarios. The results thoroughly evidence the superiority of DCTN framework that resists negative transfers across domains and tasks.

Deep Joint Semantic Adaptation Network for Multi-source Unsupervised Domain Adaptation

This paper addresses the problem of land-cover map updating by classification of multitemporal remote-sensing images in the context of domain adaptation (DA). The basic assumptions behind the proposed approach are twofold. The first one is that training data (ground reference information) are available for one of the considered multitemporal acquisitions (source domain) whereas they are not for the other (target domain). The second one is that multitemporal acquisitions (i.e., target and source domains) may be characterized by different sets of classes. Unlike other approaches available in the literature, the proposed DA Bayesian classifier based on maximum a posteriori decision rule (DA-MAP) automatically identifies whether there exist differences between the set of classes in the target and source domains and properly handles these differences in the updating process. The proposed method was tested in different scenarios of increasing complexity related to multitemporal image classification. Experimental results on medium-resolution and very high resolution multitemporal remote-sensing data sets confirm the effectiveness and the reliability of the proposed DA-MAP classifier.

Domain adaptation has achieved promising results in many areas, such as image classification and object recognition. Although a lot of algorithms have been proposed to solve the task with different domain distributions, it remains a challenge for multi-source unsupervised domain adaptation. In addition, most of the existing algorithms learn a classifier on the source domain and predict the labels for the target data, which indicates that only the knowledge derived from the hyperplane is transferred to the target domain and the structure information is ignored. In light of this, we propose a novel algorithm for multi-source unsupervised domain adaptation. Generally speaking, we aim to preserve the whole structure from source domains and transfer it to serve the task on the target domain. The source and target data are put together for clustering, which simultaneously explores the structures of the source and target domains. The structure-preserved information from source domain further guides the clustering process on the target domain. Extensive experiments on two widely used databases on object recognition and face identification show the substantial improvement of our proposed approach over several state-of-the-art methods. Especially, our algorithm can take use of multi-source domains and achieve robust and better performance compared with the single source domain adaptation methods.

In the absence of the labeled samples in a domain referred to as target domain, Domain Adaptation (DA) techniques come in handy. Generally, DA techniques assume there are available source domains that share similar predictive function with the target domain. Two core challenges of DA typically arise, variance that exists between source and target domains, and the inherent source hypothesis bias. In this paper, we first propose a Stability Transfer criterion for selecting relevant source domains with low variance. With this criterion, we introduce a TARget learning Assisted by Source Classifier Adaptation (TARASCA) method to address the two core challenges that have impeded the performances of DA techniques. To verify the robustness of TARASCA, extensive experimental studies are carried out with comparison to several state-of-the-art DA methods on the real-world Sentiment and Newsgroups datasets, where various settings for the class ratios of the source and target domains are considered.

As a branch of domain adaptation (DA), multi-source DA (MSDA) is a challenging issue that aims to transfer knowledge from multiple well-labeled source domains to a target domain for target tasks. However, most existing related works focus on single-target domain adaptation, and multiple target domain adaptation is not accounted for. We believe that multiple target domains provide valuable knowledge. Meanwhile, in multi-source and multi-target adaptation scenarios, feature generators with static parameters have difficulty generating deep features of each individual domain. In this paper, we propose a Dynamic Generator With Attention (DGWA) method for multi-source and multi-target domain adaptation to adapt domain-agnostic deep features in a multi-source and multi-target domain scenario. The feature generator with dynamic parameters can dynamically change its parameters with data input from different domains, which greatly improves the generalization of the feature pools. An attention mechanism is used in our DGWA to learn more transferable information from different domains. To demonstrate the performance of DGWA, we conduct extensive experiments on several popular domain adaptation datasets, including the digits, Office+Caltech10, Office-Home, and ImageCLEF-DA datasets. The experimental results demonstrate that our method performs better than state-of-the-art methods.

Artificial intelligence combined with Raman spectroscopy for disease diagnosis is on the rise. However, these methods require a large amount of annotated spectral data for modeling to achieve high diagnostic accuracy. Annotating labels consumes significant medical resources and time. To reduce dependence on labeled medical data resources, we propose a method called Multisource Unsupervised Raman Spectroscopy Domain Adaptation Model with Reconstructed Target Domains (MURDA). It transfers knowledge learned from source domain data sets of different diseases to an unlabeled target domain data set. Compared to knowledge transfer from a single source domain, knowledge from multiple disease source domains provides more generalized knowledge. Considering the diversity of autoimmune diseases and the limited sample size, we apply MURDA to assist in the medical diagnosis of autoimmune diseases. Additionally, we propose a Double-Branch Multiscale Convolutional Self-Attention (DMCS) feature extractor that is more suitable for spectral data feature extraction. On three sets of serum Raman spectroscopy data sets for autoimmune diseases, the multisource domain adaptation diagnostic accuracy of MURDA was superior to traditional single source and multisource models, with accuracy rates of 73.6%, 83.4%, and 82.9%, respectively. Compared with pure source tasks without domain adaptation, it improved by 15.1%, 36%, and 21.6%, respectively. This demonstrates the effectiveness of Raman spectroscopy combined with MURDA in diagnosing autoimmune diseases. We investigated the important decision dependency peaks in migration tasks, providing assistance for future research on artificial intelligence combined with Raman spectroscopy for diagnosing autoimmune diseases. Furthermore, to validate the effectiveness and generalization performance of MURDA, we conducted experiments on the publicly available RRUFF data set, exploring the application of multisource unsupervised domain adaptation in more Raman spectroscopy scenarios.

Remaining useful life prediction under variable operating conditions via multisource adversarial domain adaptation networks

In many real-world applications, the domain of model learning (referred as source domain) is usually inconsistent with or even different from the domain of testing (referred as target domain), which makes the learnt model degenerate in target domain, i.e., the test domain. To alleviate the discrepancy between source and target domains, we propose a domain adaptation method, named as Bi-shifting Auto-Encoder network (BAE). The proposed BAE attempts to shift source domain samples to target domain, and also shift the target domain samples to source domain. The non-linear transformation of BAE ensures the feasibility of shifting between domains, and the distribution consistency between the shifted domain and the desirable domain is constrained by sparse reconstruction between them. As a result, the shifted source domain is supervised and follows similar distribution as target domain. Therefore, any supervised method can be applied on the shifted source domain to train a classifier for classification in target domain. The proposed method is evaluated on three domain adaptation scenarios of face recognition, i.e., domain adaptation across view angle, ethnicity, and imaging sensor, and the promising results demonstrate that our proposed BAE can shift samples between domains and thus effectively deal with the domain discrepancy.