Diffusion‐UDA: Diffusion‐based unsupervised domain adaptation for submersible fault diagnosis
Electronics LettersDeep learning has demonstrated notable success in mechanical signal processing with a large amount labelled data. However, the systems of the Jiaolong deep‐sea submersible prone to malfunction are typically diverse, due to the high complexity of its ...
Penghui Zhao +5 more
doaj +2 more sources
Prototype-oriented class-conditional clustering transport for unsupervised domain adaptation [PDF]
Scientific ReportsUnsupervised domain adaptation (UDA) plays a vital role in machine learning to tackle the homogeneous data distribution scenario. While most previous studies have concentrated on between-domain transferability, they often neglect the rich within-domain ...
Liangda Yan, Jianwen Tao, Tao He
doaj +2 more sources
A simple preprocessing approach for improving semantic segmentation in unsupervised domain adaptation [PDF]
Scientific ReportsUnsupervised Domain Adaptation (UDA) is a powerful strategy for bridging the gap between synthetic (source) data and real-world (target) data, thereby reducing expensive manual annotations. In this work, we propose ProCST, a novel preprocessing framework
Shahaf Ettedgui +2 more
doaj +2 more sources
TransConv: Transformer Meets Contextual Convolution for Unsupervised Domain Adaptation [PDF]
EntropyUnsupervised domain adaptation (UDA) aims to reapply the classifier to be ever-trained on a labeled source domain to a related unlabeled target domain. Recent progress in this line has evolved with the advance of network architectures from convolutional ...
Junchi Liu, Xiang Zhang, Zhigang Luo
doaj +2 more sources
Source-free domain adaptation for semantic image segmentation using internal representations [PDF]
Frontiers in Big DataSemantic segmentation models trained on annotated data fail to generalize well when the input data distribution changes over extended time period, leading to requiring re-training to maintain performance.
Serban Stan, Mohammad Rostami
doaj +2 more sources
Scale-Consistent and Temporally Ensembled Unsupervised Domain Adaptation for Object Detection [PDF]
SensorsUnsupervised Domain Adaptation for Object Detection (UDA-OD) aims to adapt a model trained on a labeled source domain to an unlabeled target domain, addressing challenges posed by domain shifts. However, existing methods often face significant challenges,
Lunfeng Guo +4 more
doaj +2 more sources
HDRSeg-UDA: Semantic Segmentation for HDR Images with Unsupervised Domain Adaptation
Smart CitiesAccurate detection and localization of traffic objects are essential for autonomous driving tasks such as path planning. While semantic segmentation is able to provide pixel-level classification, existing networks often fail under challenging conditions ...
Huei-Yung Lin, Ming-Yiao Chen
doaj +2 more sources
Meta-UDA: Unsupervised Domain Adaptive Thermal Object Detection using Meta-Learning [PDF]
2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022 Accepted to WACV ...
VS, Vibashan +4 more
openaire +2 more sources
LE-UDA: Label-Efficient Unsupervised Domain Adaptation for Medical Image Segmentation
IEEE Transactions on Medical Imaging, 2023 Accepted by IEEE Transactions on Medical Imaging ...
Ziyuan Zhao +5 more
openaire +3 more sources
Multibranch Unsupervised Domain Adaptation Network for Cross Multidomain Orchard Area Segmentation
Remote Sensing, 2022 Although unsupervised domain adaptation (UDA) has been extensively studied in remote sensing image segmentation tasks, most UDA models are designed based on single-target domain settings.
Ming Liu +3 more
doaj +1 more source