Results 1 to 10 of about 389,599 (264)
Prototype contrastive and adversarial alignment for heterogeneous domain adaptation [PDF]
Scientific ReportsHeterogeneous 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
Multi-EPL: Accurate multi-source domain adaptation
PLoS ONE, 2021 Given multiple source datasets with labels, how can we train a target model with no labeled data? Multi-source domain adaptation (MSDA) aims to train a model using multiple source datasets different from a target dataset in the absence of target data ...
Seongmin Lee, Hyunsik Jeon, U. Kang
doaj +2 more sources
Unsupervised domain adaptation with post-adaptation labeled domain performance preservation
Machine Learning with Applications, 2022 Unsupervised domain adaptation is a machine learning-oriented application that aims to transfer knowledge learned from a seen (source) domain with labeled data to an unseen (target) domain with only unlabeled data.
Haidi Badr, Nayer Wanas, Magda Fayek
doaj +1 more source
NuSegDA: Domain adaptation for nuclei segmentation
Frontiers in Big Data, 2023 The accurate segmentation of nuclei is crucial for cancer diagnosis and further clinical treatments. To successfully train a nuclei segmentation network in a fully-supervised manner for a particular type of organ or cancer, we need the dataset with ...
Mohammad Minhazul Haq +2 more
doaj +1 more source
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
FDDS: Feature Disentangling and Domain Shifting for Domain Adaptation
Mathematics, 2023 Domain adaptation is a learning strategy that aims to improve the performance of models in the current field by leveraging similar domain information. In order to analyze the effects of feature disentangling on domain adaptation and evaluate a model’s ...
Huan Chen, Farong Gao, Qizhong Zhang
doaj +1 more source
IEEE Access, 2023 In traditional machine learning, the training and testing data are assumed to come from the same independent and identical distributions. This assumption, however, does not hold up in real-world applications, as differences between the training and ...
Obsa Gilo +3 more
doaj +1 more source
Sensors, 2022 Unsupervised domain adaptation, which aims to alleviate the domain shift between source domain and target domain, has attracted extensive research interest; however, this is unlikely in practical application scenarios, which may be due to privacy issues ...
Xuejun Zhao +6 more
doaj +1 more source
Spectral Normalization for Domain Adaptation
Information, 2020 The transfer learning method is used to extend our existing model to more difficult scenarios, thereby accelerating the training process and improving learning performance.
Liquan Zhao, Yan Liu
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