Results 91 to 100 of about 3,036,262 (193)

Adversarial Learning and Interpolation Consistency for Unsupervised Domain Adaptation

IEEE Access, 2019
Unsupervised domain adaptation (UDA) aims to learn a prediction model for the target domain given labeled source data and unlabeled target data. Impressive progress has been made by adversarial learning-based methods that align distributions across ...
Xin Zhao, Shengsheng Wang
doaj   +1 more source

DDS-UDA: Dual-domain synergy for unsupervised domain adaptation in joint segmentation of optic disc and optic cup

Medical Image Analysis
Convolutional neural networks (CNNs) have achieved exciting performance in joint segmentation of optic disc and optic cup on single-institution datasets. However, their clinical translation is hindered by two major challenges: limited availability of large-scale, high-quality annotations and performance degradation caused by domain shift during ...
Yusong Xiao, Yuxuan Wu, Li Xiao, Gang Qu, Haiye Huo, Yu-Ping Wang   +5 more
openaire   +2 more sources

VFM-UDA++: Improving Network Architectures and Data Strategies for Unsupervised Domain Adaptive Semantic Segmentation

2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
Unsupervised Domain Adaptation (UDA) enables strong generalization from a labeled source domain to an unlabeled target domain, often with limited data. In parallel, Vision Foundation Models (VFMs) pretrained at scale without labels have also shown impressive downstream performance and generalization.
Brunó Bence Englert, Gijs Dubbelman
openaire   +3 more sources

EDIF: boosting unsupervised cross-domain forest fire smoke detection with enhanced domain-invariant features

Geomatics, Natural Hazards & Risk
In forest fire smoke detection tasks, variations in data distribution caused by deployment environments, acquisition devices, and smoke characteristics, along with the scarcity of fire incidents, make it difficult for models to generalize across all ...
Peixian Jin, Xuhong Feng, Pengle Cheng, Mingyu Wang, Xiaodong Liu, Ying Huang   +5 more
doaj   +1 more source

CVKD-UDA: Cross-View Knowledge Distillation for 3D Unsupervised Domain Adaptive Segmentation

IEEE Transactions on Multimedia
3D unsupervised domain adaptive (UDA) segmentation mitigates the high cost of manual annotations of the new domain data. Self-training has emerged as the dominant approach in this area, where its success heavily depends on a well-initialized warm-up model to generate reliable pseudo labels.
Yuan, Zhimin, Cheng, Ming, Yu, Shangshu, Li, Wen, Liu, Dunqiang, Huang, Xin, Wang, Cheng   +6 more
openaire   +2 more sources

PPLM-Net: Partial Patch Local Masking Net for Remote Sensing Image Unsupervised Domain Adaptation Classification

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
In remote sensing image classification task, it is often apply a model trained on one dataset (source domain) to another dataset (target domain). However, due to the presence of domain shift between these domains where data are not independent and ...
Junsong Leng, Zhong Chen, Haodong Mu, Tianhang Liu, Hanruo Chen, Guoyou Wang   +5 more
doaj   +1 more source

Convolutional Neural Networks for Road Detection: An Unsupervised Domain Adaptation Approach [PDF]

The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Due to the frequent road network changes, keeping them updated is fundamental for several purposes. Currently, models based on Deep Learning (DL), specifically, Convolutional Neural Networks (CNNs), such as encoder-decoder type, are state-of-the-art for ...
G. R. Collegio, A. P. Dal Poz, A. G. G. Filho, A. Habib   +3 more
doaj   +1 more source

Spatial-Topological-Semantic alignment for cross domain scene classification of remote sensing images with few source labels

International Journal of Applied Earth Observations and Geoinformation
Domain adaptation is crucial for information integration of remote sensing systems, such as satellite constellations and space stations, to intelligently achieving full domain awareness. The conventional methods focus on aligning spatial features without
Binquan Li, Lishuang Gong, Qiao Wang, Xin Guo, Zhiqiang Li   +4 more
doaj   +1 more source

RAAN: A Gaussian Prior Domain Adaptive Network for Rolling Bearing Fault Diagnosis Under Variable Working Conditions

Complex System Modeling and Simulation
In the field of fault diagnosis for rolling bearings under variable working conditions, significant progress has been made using methods based on unsupervised domain adaptation (UDA). However, most existing UDA methods primarily achieve identification by
Kang Liu, Yang Yu, Yuanjiang Li, Tao Lang, Ruochen Liu   +4 more
doaj   +1 more source

ToMo-UDA++: Unsupervised Domain Adaptation for Anatomical Structure Detection Using Enhanced Topology and Morphology Knowledge

International Journal of Computer Vision
Abstract In clinical practice, the detection of key anatomical structures/organs in medical images is critical for a range of downstream tasks, such as quality control and diagnosis. However, deep learning-based models trained on medical images from one institution/device typically experience a performance decline
Bin Pu, Jiewen Yang, Xingguo Lv, Xingbo Dong, Lei Zhao 0013, Shengli Li 0001, Kenli Li 0001, Xiaomeng Li 0001   +7 more
openaire   +2 more sources