Results 11 to 20 of about 2,905 (180)

Histogram matching-enhanced adversarial learning for unsupervised domain adaptation in medical image segmentation. [PDF]

Med Phys
Abstract Background Unsupervised domain adaptation (UDA) seeks to mitigate the performance degradation of deep neural networks when applied to new, unlabeled domains by leveraging knowledge from source domains. In medical image segmentation, prevailing UDA techniques often utilize adversarial learning to address domain shifts for cross‐modality ...
Qian X, Shao HC, Li Y, Lu W, Zhang Y.
europepmc   +2 more sources

Unsupervised Domain Adaptation Based on Pseudo-Label Confidence

IEEE Access, 2021
Unsupervised domain adaptation aims to align the distributions of data in source and target domains, as well as assign the labels to data in the target domain.
Tingting Fu, Ying Li
doaj   +1 more source

Unsupervised Black-Box Model Domain Adaptation for Brain Tumor Segmentation

Frontiers in Neuroscience, 2022
Unsupervised domain adaptation (UDA) is an emerging technique that enables the transfer of domain knowledge learned from a labeled source domain to unlabeled target domains, providing a way of coping with the difficulty of labeling in new domains.
Xiaofeng Liu, Chaehwa Yoo, Chaehwa Yoo, Fangxu Xing, C.-C. Jay Kuo, Georges El Fakhri, Je-Won Kang, Je-Won Kang, Jonghye Woo   +8 more
doaj   +1 more source

Domain‐adapted driving scene understanding with uncertainty‐aware and diversified generative adversarial networks

CAAI Transactions on Intelligence Technology, EarlyView., 2023
Abstract Autonomous vehicles are required to operate in an uncertain environment. Recent advances in computational intelligence techniques make it possible to understand driving scenes in various environments by using a semantic segmentation neural network, which assigns a class label to each pixel.
Yining Hua, Jie Sui, Hui Fang, Chuan Hu, Dewei Yi   +4 more
wiley   +1 more source

On the Importance of Attention and Augmentations for Hypothesis Transfer in Domain Adaptation and Generalization

Sensors, 2023
Unsupervised domain adaptation (UDA) aims to mitigate the performance drop due to the distribution shift between the training and testing datasets. UDA methods have achieved performance gains for models trained on a source domain with labeled data to a ...
Rajat Sahay, Georgi Thomas, Chowdhury Sadman Jahan, Mihir Manjrekar, Dan Popp, Andreas Savakis   +5 more
doaj   +1 more source

T-UDA: Temporal Unsupervised Domain Adaptation in Sequential Point Clouds

2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023
Deep perception models have to reliably cope with an open-world setting of domain shifts induced by different geographic regions, sensor properties, mounting positions, and several other reasons. Since covering all domains with annotated data is technically intractable due to the endless possible variations, researchers focus on unsupervised domain ...
Gebrehiwot, Awet Haileslassie, Hurych, David, Zimmermann, Karel, Pérez, Patrick, Svoboda, Tomáš   +4 more
openaire   +2 more sources

Unsupervised Cross-Scene Aerial Image Segmentation via Spectral Space Transferring and Pseudo-Label Revising

Remote Sensing, 2023
Unsupervised domain adaptation (UDA) is essential since manually labeling pixel-level annotations is consuming and expensive. Since the domain discrepancies have not been well solved, existing UDA approaches yield poor performance compared with ...
Wenjie Liu, Wenkai Zhang, Xian Sun, Zhi Guo   +3 more
doaj   +1 more source

UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimation

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
Accepted to CVPR ...
Lee, Taeyeop, Lee, Byeong-Uk, Shin, Inkyu, Choe, Jaesung, Shin, Ukcheol, Kweon, In So, Yoon, Kuk-Jin   +6 more
openaire   +2 more sources

SF-UDA^3D: Source-Free Unsupervised Domain Adaptation for LiDAR-Based 3D Object Detection [PDF]

2020 International Conference on 3D Vision (3DV), 2020
3D object detectors based only on LiDAR point clouds hold the state-of-the-art on modern street-view benchmarks. However, LiDAR-based detectors poorly generalize across domains due to domain shift. In the case of LiDAR, in fact, domain shift is not only due to changes in the environment and in the object appearances, as for visual data from RGB cameras,
Saltori, Cristiano, Lathuiliére, Stéphane, Sebe, Nicu, Ricci, Elisa, Galasso, Fabio   +4 more
openaire   +3 more sources

LiDAR-UDA: Self-ensembling Through Time for Unsupervised LiDAR Domain Adaptation

2023 IEEE/CVF International Conference on Computer Vision (ICCV), 2023
We introduce LiDAR-UDA, a novel two-stage self-training-based Unsupervised Domain Adaptation (UDA) method for LiDAR segmentation. Existing self-training methods use a model trained on labeled source data to generate pseudo labels for target data and refine the predictions via fine-tuning the network on the pseudo labels.
Shaban, Amirreza, Lee, JoonHo, Jung, Sanghun, Meng, Xiangyun, Boots, Byron   +4 more
openaire   +2 more sources