Results 41 to 50 of about 1,321,207 (310)
IET Computer Vision, 2020 Unsupervised domain adaption aims to reduce the divergence between the source domain and the target domain. The final objective is to learn domain‐invariant features from both domains that get the minimised expected error on the target domain.
Xingmei Wang, Boxuan Sun, Hongbin Dong
doaj +1 more source
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 +2 more sources
Cogent Arts & Humanities, 2023 This study aims to investigate metaphorical representation in Javanese food names in terms of linguistic forms, metaphorical element distribution, similarity basis, source domains, and sociocultural factors underlying their existence. This study employed
Hendrokumoro +2 more
doaj +1 more source
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
Terahertz pump-probe experiment at the synchrotron light source MLS [PDF]
, 2013 We have developed a pump-probe experiment utilizing broad-band coherent terahertz synchrotron radiation provided by the Metrology Light Source (MLS).
H.-W. Hubers +15 more
core +1 more source
Probabilistic Modeling Paradigms for Audio Source Separation [PDF]
, 2010 This is the author's final version of the article, first published as E. Vincent, M. G. Jafari, S. A. Abdallah, M. D. Plumbley, M. E. Davies. Probabilistic Modeling Paradigms for Audio Source Separation. In W.
Davies, ME +14 more
core +1 more source
IEEE Access, 2020 Recently, neural networks have shown promising results for named entity recognition(NER), which needs a number of labeled data to for model training. When meeting a new domain (target domain) for NER, there is no or a few labeled data, which makes domain
Chuanbo Liu +3 more
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 +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
Two-Dimensional Iterative Source-Channel Decoding for Distributed Video Coding [PDF]
, 2014 Motivated by the Joint Source-Channel Decoding (JSCD) principle of exploiting the source redundancy, in this treatise we study the application of iterative source-channel decoding (ISCD) conceived for distributed video coding (DVC), where the video ...
Wang, Tao +3 more
core +1 more source