Results 11 to 20 of about 12,484 (262)
Cross-Domain Contrastive Learning for Unsupervised Domain Adaptation [PDF]
IEEE Transactions on Multimedia, 2023 IEEE Transactions on ...
Rui Wang +5 more
openaire +4 more sources
Self-Adaptation for Unsupervised Domain Adaptation [PDF]
Proceedings - Natural Language Processing in a Deep Learning World, 2019 Lack of labelled data in the target domain for training is a common problem in domain adaptation. To overcome this problem, we propose a novel unsupervised domain adaptation method that combines projection and self-training based approaches. Using the labelled data from the source domain, we first learn a projection that maximises the distance among ...
Cui, Xia, Bollegala, Danushka
openaire +2 more sources
ACDC: Online unsupervised cross-domain adaptation
Knowledge-Based Systems, 2022 We consider the problem of online unsupervised cross-domain adaptation, where two independent but related data streams with different feature spaces -- a fully labeled source stream and an unlabeled target stream -- are learned together. Unique characteristics and challenges such as covariate shift, asynchronous concept drifts, and contrasting data ...
Marcus de Carvalho +3 more
openaire +4 more sources
Bilateral co-transfer for unsupervised domain adaptation
Journal of Automation and Intelligence, 2023 Labeled data scarcity of an interested domain is often a serious problem in machine learning. Leveraging the labeled data from other semantic-related yet co-variate shifted source domain to facilitate the interested domain is a consensus.
Fuxiang Huang, Jingru Fu, Lei Zhang
doaj +1 more source
Test-Time Unsupervised Domain Adaptation [PDF]
, 2020 Convolutional neural networks trained on publicly available medical imaging datasets (source domain) rarely generalise to different scanners or acquisition protocols (target domain). This motivates the active field of domain adaptation. While some approaches to the problem require labeled data from the target domain, others adopt an unsupervised ...
Varsavsky, Thomas +5 more
openaire +3 more sources
Unsupervised Adversarial Domain Adaptation for Agricultural Land Extraction of Remote Sensing Images
Remote Sensing, 2022 Agricultural land extraction is an essential technical means to promote sustainable agricultural development and modernization research. Existing supervised algorithms rely on many finely annotated remote-sensing images, which is both time-consuming and ...
Junbo Zhang +5 more
doaj +1 more source
Benchmarking Domain Adaptation Methods on Aerial Datasets
Sensors, 2021 Deep learning grew in importance in recent years due to its versatility and excellent performance on supervised classification tasks. A core assumption for such supervised approaches is that the training and testing data are drawn from the same ...
Navya Nagananda +6 more
doaj +1 more source
Multi-Step Online Unsupervised Domain Adaptation [PDF]
ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020 In this paper, we address the Online Unsupervised Domain Adaptation (OUDA) problem, where the target data are unlabelled and arriving sequentially. The traditional methods on the OUDA problem mainly focus on transforming each arriving target data to the source domain, and they do not sufficiently consider the temporal coherency and accumulative ...
Moon, J. H. +2 more
openaire +2 more sources
Inferring Latent Domains for Unsupervised Deep Domain Adaptation [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021 Unsupervised Domain Adaptation (UDA) refers to the problem of learning a model in a target domain where labeled data are not available by leveraging information from annotated data in a source domain. Most deep UDA approaches operate in a single-source, single-target scenario, i.e.
Massimiliano Mancini +4 more
openaire +6 more sources
Cross Domain Mean Approximation for Unsupervised Domain Adaptation
IEEE Access, 2020 Unsupervised Domain Adaptation (UDA) aims to leverage the knowledge from the labeled source domain to help the task of target domain with the unlabeled data. It is a key step for UDA to minimize the cross-domain distribution divergence. In this paper, we
Shaofei Zang +4 more
doaj +1 more source