Results 91 to 100 of about 3,613,102 (160)

Domain-guided conditional diffusion model for unsupervised domain adaptation

open access: yes
Limited transferability hinders the performance of a well-trained deep learning model when applied to new application scenarios. Recently, Unsupervised Domain Adaptation (UDA) has achieved significant progress in addressing this issue via learning domain-
Zhang, Yulong   +5 more
core   +1 more source

VLMs meet UDA: Boosting Transferability of Open Vocabulary Segmentation with Unsupervised Domain Adaptation [PDF]

open access: yes
Segmentation models are typically constrained by the categories defined during training. To address this, researchers have explored two independent approaches: adapting Vision-Language Models (VLMs) and leveraging synthetic data.
Alcover-Couso, Roberto   +3 more
core   +1 more source

A hybrid framework for unsupervised domain adaptation: Integrating feature alignment, parameter adaptation, and instance selection

open access: yesJournal of King Saud University: Computer and Information Sciences
Unsupervised Domain Adaptation (UDA), a key subfield of Transfer Learning (TL), addresses the performance degradation caused by domain shift that occurs when a model trained on a labeled source domain is applied to an unlabeled target domain.
Shaofei Zang   +6 more
doaj   +1 more source

Multi-level domain perturbation for source-free object detection in remote sensing images

open access: yesGeo-spatial Information Science
Recent advancements in cross-domain object detection have primarily relied on unsupervised domain adaptation (UDA) techniques to bridge domain gaps in remote sensing images.
Weixing Liu   +4 more
doaj   +1 more source

Domain-Constraint Transfer Coding for Imbalanced Unsupervised Domain Adaptation

open access: yes, 2016
Unsupervised domain adaptation (UDA) deals with the task that labeled training and unlabeled test data collected from source and target domains, respectively.
Wang, Yu-Chiang Frank   +9 more
core   +1 more source

UNSUPERVISED ADAPTATION FROM FDG TO PSMA PET/CT FOR 3D LESION DETECTION UNDER LABEL SHIFT. [PDF]

open access: yesProc IEEE Int Symp Biomed Imaging
Liu X   +5 more
europepmc   +1 more source

Multi-Task Reconstruction Strategies for Unsupervised 3D Domain Adaptation

open access: yes
This thesis addresses the challenge of domain shift in 3D point cloud data through innovative Unsupervised Domain Adaptation (UDA) methods. Focusing on enhancing existing techniques for point cloud classification to minimize distribution shifts, the ...
Donati, Matteo
core  

Home - About - Disclaimer - Privacy