Results 81 to 90 of about 3,036,262 (193)

Domain-Guided Conditional Diffusion Model for Unsupervised Domain Adaptation [PDF]

, 2023
Limited transferability hinders the performance of deep learning models when applied to new application scenarios. Recently, Unsupervised Domain Adaptation (UDA) has achieved significant progress in addressing this issue via learning domain-invariant ...
Zhang, Yulong, Lu, Jiangang, Zhang, Yu, Kwok, James T., Chen, Shuhao, Jiang, Weisen   +5 more
core   +1 more source

Efficient unsupervised domain adaptation for crack segmentation with interpretable Fourier– Morphology blending and Uncertainty‐guided self‐training

Computer-Aided Civil and Infrastructure Engineering, Volume 40, Issue 29, Page 5790-5807, 9 December 2025.
Abstract Automated crack segmentation models are vital for infrastructure monitoring but fail when deployed in new domains. Overcoming this domain shift without costly re‐annotation is vital. This paper presents a novel unsupervised domain adaptation framework that uniquely integrates Fourier‐based style transfer with targeted morphological operators ...
Saheli Bhattacharya, Chen Zhang, Dhanada K. Mishra, Matthew M. F. Yuen, Jize Zhang   +4 more
wiley   +1 more source

Domain-Invariant Feature Learning for Domain Adaptation

, 2023
Unsupervised domain adaptation (UDA) explores mainly how to learn domain-invariant features from the source domain when the target domain label is unknown.
Ching-Ting Tu; Hsiau-Wen Lin; Hwei Jen Lin; Yoshimasa Tokuyama; Chia-Hung Chu
core   +1 more source

Co-regularized alignment for unsupervised domain adaptation

, 2019
Deep neural networks, trained with large amount of labeled data, can fail to generalize well when tested with examples from a target domain whose distribution differs from the training data distribution, referred as the source domain. It can be expensive
Freeman, William T., Feris, Rogerio, Wornell, Gregory, Karlinsky, Leonid, Wadhawan, Kahini, Sattigeri, Prasanna, Kumar, Abhishek   +6 more
core  

Model adaptation via credible local context representation

CAAI Transactions on Intelligence Technology, Volume 10, Issue 3, Page 638-651, June 2025.
Abstract Conventional model transfer techniques, requiring the labelled source data, are not applicable in the privacy‐protected medical fields. For the challenging scenarios, recent source data‐free domain adaptation (SFDA) has become a mainstream solution but losing focus on the inter‐sample class information. This paper proposes a new Credible Local
Song Tang, Wenxin Su, Yan Yang, Lijuan Chen, Mao Ye   +4 more
wiley   +1 more source

TransConv: Transformer Meets Contextual Convolution for Unsupervised Domain Adaptation

Entropy
Unsupervised 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   +1 more source

High‐Throughput Robotic Phenotyping for Quantifying Tomato Disease Severity Enabled by Synthetic Data and Domain‐Adaptive Semantic Segmentation

Journal of Field Robotics, Volume 42, Issue 3, Page 657-678, May 2025.
ABSTRACT Plant diseases cause an annual global crop loss of 20%–40%, leading to estimated economic losses of 30–50 billion dollars. Tomatoes are susceptible to more than 200 diseases. Breeding disease‐resistant cultivars is more cost‐effective and environmentally sustainable than the frequent use of pesticides.
Weilong He, Xingjian Li, Zhenghua Zhang, Yuxi Chen, Jianbo Zhang, Dilip R. Panthee, Inga Meadows, Lirong Xiang   +7 more
wiley   +1 more source

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

Geo-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, Jun Liu, Xin Su, Han Nie, Bin Luo   +4 more
doaj   +1 more source

A semi‐supervised domain adaptation method with scale‐aware and global‐local fusion for abdominal multi‐organ segmentation

Journal of Applied Clinical Medical Physics, Volume 26, Issue 3, March 2025.
Abstract Background Abdominal multi‐organ segmentation remains a challenging task. Semi‐supervised domain adaptation (SSDA) has emerged as an innovative solution. However, SSDA frameworks based on UNet struggle to capture multi‐scale and global information.
Kexin Han, Qiong Lou, Fang Lu
wiley   +1 more source

Unsupervised domain adaptation by domain invariant projection [PDF]

, 2013
Domain-invariant representations are key to addressing the domain shift problem where the training and test exam-ples follow different distributions.
Mahsa Baktashmotlagh, Brian C. Lovell, Mehrtash T. Har, Harandi, Mehrtash T., Salzmann, M., Mathieu Salzmann, Lovell, Brian C., Baktashmotlagh, M., Mehrtash T. Harandi   +8 more
core   +1 more source