Domain adaptation is a powerful tool for transferring the knowledge of the source domain with sufficient annotations for target tasks. However, most existing domain adaptation methods focus on the single-source鈥
An alternative set-up for domain adaptation with multiple sources is one where the learner is not supplied with a good hypothesis h i for each source but where instead he has access to the labeled training data for each source domain. A natural solution consists then of combining the raw lab...
Domain adaptation with multiple sources. The UDA methods mentioned above mainly consider target vs. single source. If multiple sources are available, the domain shift among sources should also be account for. The research originates from A-SVM [49] that leverages the ensemble of source-specific ...
Domain Adaptation - 领域自适应1. 【Domain Adaptation】Unsupervised Bidirectional Cross-Modality Adaptation via Deeply Synergistic Image and Feature Alignment for Medical Image Segmentation 【领域自…
Firstly, it would be interesting to investigate algorithms that choose a convex combination of multiple sources to minimize the bound in [3] as possible approaches to adaptation from multiple sources. In addition, the error bound given in [28] is defined on a fixed target distribution. ...
Domain adaptation (DA) is the topical problem of adapting models from labelled source datasets so that they perform well on target datasets where only unlabelled or partially labelled data is available. Many methods have been proposed to address this pro
Theoretically, domain adaptation is a well-researched problem. Further, this theory has been well-used in practice. In particular, we note the bound on tar
Domain adaptation (DA) offers a valuable means to reuse data and models for new problem domains. However, robust techniques have not yet been considered for time series data with varying amounts of data availability. In our paper, we make three main contributions to fill this gap. First, we...
domain adaptation research in medical images, we refer to the very recent survey by Guan et al.37. Unsupervised DA gained growing attention in recent years with the advance of generative adversarial networks (GANs)38. Adversarial DA applies one or multiple discriminator networks to align the ...
Domain-specific sentiment classification via fusing sentiment knowledge from multiple sources Inf. Fusion (2017) ZhaoC. et al. Multi-source domain adaptation with joint learning for cross-domain sentiment classification Knowl.-Based Syst. (2020) DuY. et al. Wasserstein based transfer network for cros...