Results 41 to 50 of about 7,549,002 (298)
Acta Neophilologica, 2023 The article discusses ontological metaphors with the target domain HEART in the text of the New Testament. It aims at exploring cross-domain mappings through the analysis of metaphoric expressions, involving lexeme heart, obtained by the Bible corpus ...
Eldar Veremchuk
doaj +1 more source
Domain Aggregation Networks for Multi-Source Domain Adaptation
CoRR, 2019 In many real-world applications, we want to exploit multiple source datasets of similar tasks to learn a model for a different but related target dataset -- e.g., recognizing characters of a new font using a set of different fonts. While most recent research has considered ad-hoc combination rules to address this problem, we extend previous work on ...
Junfeng Wen +2 more
openaire +4 more sources
Universal Source-Free Domain Adaptation
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020 There is a strong incentive to develop versatile learning techniques that can transfer the knowledge of class-separability from a labeled source domain to an unlabeled target domain in the presence of a domain-shift. Existing domain adaptation (DA) approaches are not equipped for practical DA scenarios as a result of their reliance on the knowledge of ...
Jogendra Nath Kundu +3 more
openaire +2 more sources
Multi-source domain adaptation for regression
CoRR, 2023 Multi-source domain adaptation (DA) aims at leveraging information from more than one source domain to make predictions in a target domain, where different domains may have different data distributions. Most existing methods for multi-source DA focus on classification problems while there is only limited investigation in the regression settings.
Yujie Wu, Giovanni Parmigiani, Boyu Ren
openaire +3 more sources
THE PERVASIVENESS OF METAPHOR IN THE LANGUAGE OF ECONOMICS
Studies and Scientific Researches: Economics Edition, 2015 Nowadays, metaphors can be seen in a totally new light, exceeding their primary function of being used only as ornamental tropes and becoming powerful instruments of expressiveness.
Gabriela Telibașa
doaj +1 more source
Wasserstein Barycenter for Multi-Source Domain Adaptation
, 2021 International audienceMulti-source domain adaptation is a key technique that allows a model to be trained on data coming from various probability distribution.
Mboula, Fred Maurice Ngole +3 more
core +1 more source
Universal Multi-Source Domain Adaptation
CoRR, 2020 Unsupervised domain adaptation enables intelligent models to transfer knowledge from a labeled source domain to a similar but unlabeled target domain. Recent study reveals that knowledge can be transferred from one source domain to another unknown target domain, called Universal Domain Adaptation (UDA). However, in the real-world application, there are
Yueming Yin +3 more
openaire +3 more sources
Multi-Source Survival Domain Adaptation
Proceedings of the AAAI Conference on Artificial Intelligence, 2023 Survival analysis is the branch of statistics that studies the relation between the characteristics of living entities and their respective survival times, taking into account the partial information held by censored cases. A good analysis can, for example, determine whether one medical treatment for a group of patients is better than another. With the
Ammar Shaker, Carolin Lawrence
openaire +2 more sources
Overcoming learning bias via Prototypical Feature Compensation for source-free domain adaptation [PDF]
The focus of Source-free Unsupervised Domain Adaptation (SFUDA) is to effectively transfer a well-trained model from the source domain to an unlabelled target domain.
Yu, Xiaohan +3 more
core +1 more source