Results 11 to 20 of about 8,068,927 (352)

Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering [PDF]

open access: yesTransactions of the Association for Computational Linguistics, 2022
Retrieval Augment Generation (RAG) is a recent advancement in Open-Domain Question Answering (ODQA). RAG has only been trained and explored with a Wikipedia-based external knowledge base and is not optimized for use in other specialized domains such as ...
S. Siriwardhana   +5 more
semanticscholar   +2 more sources

Prototype contrastive and adversarial alignment for heterogeneous domain adaptation [PDF]

open access: yesScientific Reports
Heterogeneous domain adaptation remains challenging due to the inconsistent feature representations and data distributions between the source and target domains. In this paper, we introduce contrastive learning into heterogeneous domain adaptation, which
Zhishu Sun, Xinru Wang, Meijing Zhang
doaj   +2 more sources

Agile Domain Adaptation

open access: yes2019 International Joint Conference on Neural Networks (IJCNN), 2019
Domain adaptation investigates the problem of leveraging knowledge from a well-labeled source domain to an unlabeled target domain, where the two domains are drawn from different data distributions. Because of the distribution shifts, different target samples have distinct degrees of difficulty in adaptation.
Jingjing Li 0001   +4 more
openaire   +4 more sources

Generalized Source-free Domain Adaptation [PDF]

open access: yesIEEE International Conference on Computer Vision, 2021
Domain adaptation (DA) aims to transfer the knowledge learned from a source domain to an unlabeled target domain. Some recent works tackle source-free domain adaptation (SFDA) where only a source pre-trained model is available for adaptation to the ...
Shiqi Yang   +4 more
semanticscholar   +3 more sources

Deep CORAL: Correlation Alignment for Deep Domain Adaptation [PDF]

open access: yesECCV Workshops, 2016
Deep neural networks are able to learn powerful representations from large quantities of labeled input data, however they cannot always generalize well across changes in input distributions.
Baochen Sun, Kate Saenko
semanticscholar   +1 more source

Domain-Augmented Domain Adaptation

open access: yesCoRR, 2022
Unsupervised domain adaptation (UDA) enables knowledge transfer from the labelled source domain to the unlabeled target domain by reducing the cross-domain discrepancy. However, most of the studies were based on direct adaptation from the source domain to the target domain and have suffered from large domain discrepancies.
Qiuhao Zeng, Tianze Luo, Boyu Wang 0004
openaire   +2 more sources

Unsupervised Domain Adaptation via Domain-Adaptive Diffusion

open access: yesCoRR, 2023
Unsupervised Domain Adaptation (UDA) is quite challenging due to the large distribution discrepancy between the source domain and the target domain. Inspired by diffusion models which have strong capability to gradually convert data distributions across a large gap, we consider to explore the diffusion technique to handle the challenging UDA task ...
Duo Peng   +3 more
openaire   +2 more sources

Generalized Domain Adaptation [PDF]

open access: yes2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021
Accepted by CVPR 2021.
Yu Mitsuzumi   +3 more
openaire   +3 more sources

Moment Matching for Multi-Source Domain Adaptation [PDF]

open access: yesIEEE International Conference on Computer Vision, 2018
Conventional unsupervised domain adaptation (UDA) assumes that training data are sampled from a single domain. This neglects the more practical scenario where training data are collected from multiple sources, requiring multi-source domain adaptation. We
Xingchao Peng   +5 more
semanticscholar   +1 more source

Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation [PDF]

open access: yesNeural Information Processing Systems, 2021
Domain adaptation (DA) aims to alleviate the domain shift between source domain and target domain. Most DA methods require access to the source data, but often that is not possible (e.g. due to data privacy or intellectual property).
Shiqi Yang   +4 more
semanticscholar   +1 more source

Home - About - Disclaimer - Privacy