Unsupervised domain adaptation with target reconstruction and label confusion in the common subspace
Sign Up to like & getrecommendations! Published in 2018 at "Neural Computing and Applications"
DOI: 10.1007/s00521-018-3846-x
Abstract: Deep neural networks can learn powerful and discriminative representations from a large number of labeled samples. However, it is typically costly to collect and annotate large-scale datasets, which limits the applications of deep learning in… read more here.
Keywords: reconstruction; domain; target; domain adaptation ... See more keywords
Bi-directional class-wise adversaries for unsupervised domain adaptation
Sign Up to like & getrecommendations! Published in 2021 at "Applied Intelligence"
DOI: 10.1007/s10489-021-02609-7
Abstract: Unsupervised domain adaptation relies on well-labeled auxiliary source domain information to get better performance on the unlabeled target domain. It has shown tremendous importance for various classification and segmentation problems. Classical methods rely on diminishing… read more here.
Keywords: class; class wise; domain adaptation; domain ... See more keywords
CLDA: an adversarial unsupervised domain adaptation method with classifier-level adaptation
Sign Up to like & getrecommendations! Published in 2020 at "Multimedia Tools and Applications"
DOI: 10.1007/s11042-020-08877-8
Abstract: Domain adaptation is an active and important research field in transfer learning. Unsupervised domain adaptation, which is better in line with real-world scenarios than supervised and semi-supervised domain adaptation, has attracted much attention and research.… read more here.
Keywords: adversarial unsupervised; domain; level; domain adaptation ... See more keywords
Adversarial unsupervised domain adaptation for 3D semantic segmentation with multi-modal learning
Sign Up to like & getrecommendations! Published in 2021 at "Isprs Journal of Photogrammetry and Remote Sensing"
DOI: 10.1016/j.isprsjprs.2021.04.012
Abstract: Abstract Semantic segmentation in 3D point-clouds plays an essential role in various applications, such as autonomous driving, robot control, and mapping. In general, a segmentation model trained on one source domain suffers a severe decline… read more here.
Keywords: domain adaptation; unsupervised domain; semantic segmentation; segmentation ... See more keywords
Symmetric co-training based unsupervised domain adaptation approach for intelligent fault diagnosis of rolling bearing
Sign Up to like & getrecommendations! Published in 2020 at "Measurement Science and Technology"
DOI: 10.1088/1361-6501/ab9841
Abstract: Conventional intelligent diagnostic model is built on the foundation that the training data and testing data are recorded under the same operating condition, which neglects the fact that the operating condition of the rotating machinery… read more here.
Keywords: symmetric training; operating condition; training; domain adaptation ... See more keywords
Unsupervised Domain Adaptation by Mapped Correlation Alignment
Sign Up to like & getrecommendations! Published in 2018 at "IEEE Access"
DOI: 10.1109/access.2018.2865249
Abstract: The goal of unsupervised domain adaptation aims to utilize labeled data from source domain to annotate the target-domain data, which has none of the labels. Existing work uses Siamese network-based models to minimize the domain… read more here.
Keywords: alignment; domain adaptation; domain; unsupervised domain ... See more keywords
Unsupervised Domain Adaptation Network With Category-Centric Prototype Aligner for Biomedical Image Segmentation
Sign Up to like & getrecommendations! Published in 2021 at "IEEE Access"
DOI: 10.1109/access.2021.3063634
Abstract: With the widespread success of deep learning in biomedical image segmentation, domain shift becomes a critical and challenging problem, as the gap between two domains can severely affect model performance when deployed to unseen data… read more here.
Keywords: image segmentation; biomedical image; unsupervised domain; segmentation ... See more keywords
A Transformer-Based Unsupervised Domain Adaptation Method for Skeleton Behavior Recognition
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Access"
DOI: 10.1109/access.2023.3274658
Abstract: In recent years, skeleton-based action recognition has received extensive attention, and a large number of researches have achieved excellent performance. This paper investigates on unsupervised domain adaptation (UDA) method (STT-DA) used in skeleton-based action recognition… read more here.
Keywords: recognition; domain adaptation; unsupervised domain; domain ... See more keywords
MCDCD: Multi-Source Unsupervised Domain Adaptation for Abnormal Human Gait Detection
Sign Up to like & getrecommendations! Published in 2021 at "IEEE Journal of Biomedical and Health Informatics"
DOI: 10.1109/jbhi.2021.3080502
Abstract: For gait analysis, especially for the detection of subtle gait abnormalities, the collected datasets involve high variability across subjects due to inherent biometric traits and movement behaviors, leading to limited detection accuracy and poor generalizability.… read more here.
Keywords: multi source; source unsupervised; unsupervised domain; gait ... See more keywords
Disentangled and Side-Aware Unsupervised Domain Adaptation for Cross-Dataset Subjective Tinnitus Diagnosis
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Journal of Biomedical and Health Informatics"
DOI: 10.1109/jbhi.2022.3225089
Abstract: EEG-based tinnitus classification is a valuable tool for tinnitus diagnosis, research, and treatments. Most current works are limited to a single dataset where data patterns are similar. But EEG signals are highly non-stationary, resulting in… read more here.
Keywords: tinnitus diagnosis; unsupervised domain; domain; side aware ... See more keywords
Target-Style-Aware Unsupervised Domain Adaptation for Object Detection
Sign Up to like & getrecommendations! Published in 2021 at "IEEE Robotics and Automation Letters"
DOI: 10.1109/lra.2021.3062333
Abstract: Vision modules running on mobility platforms, such as robots and cars, often face challenging situations such as a domain shift where the distributions of training (source) data and test (target) data are different. The domain… read more here.
Keywords: style; object detection; unsupervised domain; target ... See more keywords