NSTL国家科技图书文献中心

1. Noise-Robust Conformal Prediction for Medical Image Classification NSTL国家科技图书文献中心

Coby Penso | Jacob Goldberger - 《Machine Learning in Medical Imaging,Part II》 - International Workshop on Machine Learning in Medical Imaging | International Conference on Medical Image Computing and Computer-Assisted Intervention - 2025, - 159～168 - 共10页

摘要：Conformal Prediction (CP) quantifies network uncertainty by building a small prediction set with a pre-defined probability that the correct class is within this set. In this study we tackle the proble...

关键词： Prediction set | Conformal prediction | Label noise | Conformal score

2. De-confusing Pseudo-labels in Source-Free Domain Adaptation NSTL国家科技图书文献中心

Idit Diamant | Amir Rosenfeld ... - 《Computer Vision - ECCV 2024,Part LXXIX》 - European Conference on Computer Vision - 2025, - 108～125 - 共18页

摘要：Source-free domain adaptation aims to adapt a source-trained model to an unlabeled target domain without access to the source data. It has attracted growing attention in recent years, where existing a...

关键词： Source-free domain adaptation | Noise learning

3. A Joint Training and Confidence Calibration Procedure That is Robust to Label Noise NSTL国家科技图书文献中心

Coby Penso | Jacob Goldberger - 《2024 IEEE International Symposium on Biomedical Imaging》 - IEEE International Symposium on Biomedical Imaging - 2024, - 1～5 - 共5页

摘要：Manually annotated medical imaging data tend to have unreliable labels due to the complexity of the medical data and the considerable variability across experts. Noisy data can pose a significant chal...

关键词： Training | Computational modeling | Noise | Predictive models | Data models | Calibration | Noise robustness

4. A Conformalized Learning of a Prediction Set with Applications to Medical Imaging Classification NSTL国家科技图书文献中心

Roy Hirsch | Jacob Goldberger - 《2024 IEEE International Symposium on Biomedical Imaging》 - IEEE International Symposium on Biomedical Imaging - 2024, - 1～5 - 共5页

摘要：Medical imaging classifiers can achieve high predictive accuracy, but quantifying their uncertainty remains an unresolved challenge, which prevents their deployment in medical clinics. We present an a...

关键词： Uncertainty | Accuracy | Prediction algorithms | Classification algorithms | Medical diagnosis | Task analysis | Medical diagnostic imaging

5. PLST: A Pseudo-labels with a Smooth Transition Strategy for Medical Site Adaptation NSTL国家科技图书文献中心

Tomer Bar Natan | Hayit Greenspan ... - 《Domain Adaptation and Representation Transfer: 5th MICCAI Workshop, DART 2023, Held in Conjunction with MICCAI 2023, Vancouver, BC, Canada, October 12, 2023, Proceedings》 - MICCAI Workshop on Domain Adaptation and Representation Transfer - 2024, - 31～40 - 共10页

摘要：This study addresses the challenge of medical image segmentation when transferring a pre-trained model from one medical site to another without access to pre-existing labels. The method involves utili...

关键词： Domain shift | Domain adaptation | Self-training | Pseudo-labels

6. Confidence Calibration of a Medical Imaging Classification System That is Robust to Label Noise NSTL国家科技图书文献中心

Coby Penso | Lior Frenkel ... - 《IEEE Transactions on Medical Imaging》 - 2024,43(6) - 2050～2060 - 共11页

摘要：A classification model is calibrated if its predicted probabilities of outcomes reflect their accuracy. Calibrating neural networks is critical in medical analysis applications where clinical decision...

关键词： Calibration | Noise measurement | Training | Medical diagnostic imaging | Predictive models | Noise level | Temperature distribution

7. Domain Adaptation Using Suitable Pseudo Labels for Speech Enhancement and Dereverberation NSTL国家科技图书文献中心

Lior Frenkel | Shlomo E. Chazan ... - 《IEEE/ACM transactions on audio, speech, and language processing》 - 2024,32 - 1226～1236 - 共11页

摘要：Speech enhancement and dereverberation approaches based on neural networks are designed to learn a transformation from noisy to clean speech using supervised learning. However, networks trained in thi...

关键词： Speech enhancement | Noise measurement | Training | Task analysis | Adaptation models | Jacobian matrices | Reverberation

8. Calibration of A Regression Network Based on the Predictive Variance with Applications to Medical Images NSTL国家科技图书文献中心

Lior Frenkel | Jacob Goldberger - 《2023 IEEE 20th International Symposium on Biomedical Imaging: 20th IEEE International Symposium on Biomedical Imaging (ISBI), 18-21 April 2023, Cartagena, Colombia》 - IEEE International Symposium on Biomedical Imaging - 2023, - 1～5 - 共5页

摘要：Calibrating regression neural networks is crucial in medical imaging applications where the decision-making depends on the predicted confidence. In this study we propose a calibration procedure for re...

关键词： Neural networks | Decision making | Network architecture | Calibration | Biomedical imaging

9. PLPP: A Pseudo Labeling Post-Processing Strategy for Unsupervised Domain Adaptation NSTL国家科技图书文献中心

Tomer Bar Natan | Hayit Greenspan ... - 《2023 IEEE 20th International Symposium on Biomedical Imaging: 20th IEEE International Symposium on Biomedical Imaging (ISBI), 18-21 April 2023, Cartagena, Colombia》 - IEEE International Symposium on Biomedical Imaging - 2023, - 1～5 - 共5页

摘要：A well known problem in medical imaging is the ability to use an existing model learned on source data, in a new site. This is known as the domain shift problem. We propose a pseudo labels procedure, ...

关键词： Image segmentation | Adaptation models | Magnetic resonance imaging | Semisupervised learning | Data models | Labeling | Task analysis

10. Utilizing Perturbation of Atoms’ Positions for Equivariant Pre-Training in 3D Molecular Analysis NSTL国家科技图书文献中心

Tal Kiani | Avi Caciularu ... - 《2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing: MLSP 2023, Rome, Italy, 17-20 September 2023》 - IEEE International Workshop on Machine Learning for Signal Processing - 2023, - 1～6 - 共6页

摘要：Over the past few years, a number of Graph Neural Network (GNN) architectures have been effectively employed for molecular analysis. However, generating annotated molecular data usually requires molec...

关键词： Three-dimensional displays | Quantum chemistry | Perturbation methods | Conferences | Machine learning | Signal processing | Graph neural networks

摘要：Conformal Prediction (CP) quantifies network uncertainty by building a small prediction set with a pre-defined probability that the correct class is within this set. In this study we tackle the proble...

关键词： Prediction set | Conformal prediction | Label noise | Conformal score

摘要：Source-free domain adaptation aims to adapt a source-trained model to an unlabeled target domain without access to the source data. It has attracted growing attention in recent years, where existing a...

关键词： Source-free domain adaptation | Noise learning

摘要：Manually annotated medical imaging data tend to have unreliable labels due to the complexity of the medical data and the considerable variability across experts. Noisy data can pose a significant chal...

关键词： Training | Computational modeling | Noise | Predictive models | Data models | Calibration | Noise robustness

摘要：Medical imaging classifiers can achieve high predictive accuracy, but quantifying their uncertainty remains an unresolved challenge, which prevents their deployment in medical clinics. We present an a...

关键词： Uncertainty | Accuracy | Prediction algorithms | Classification algorithms | Medical diagnosis | Task analysis | Medical diagnostic imaging

摘要：This study addresses the challenge of medical image segmentation when transferring a pre-trained model from one medical site to another without access to pre-existing labels. The method involves utili...

关键词： Domain shift | Domain adaptation | Self-training | Pseudo-labels

摘要：A classification model is calibrated if its predicted probabilities of outcomes reflect their accuracy. Calibrating neural networks is critical in medical analysis applications where clinical decision...

关键词： Calibration | Noise measurement | Training | Medical diagnostic imaging | Predictive models | Noise level | Temperature distribution

摘要：Speech enhancement and dereverberation approaches based on neural networks are designed to learn a transformation from noisy to clean speech using supervised learning. However, networks trained in thi...

关键词： Speech enhancement | Noise measurement | Training | Task analysis | Adaptation models | Jacobian matrices | Reverberation

摘要：Calibrating regression neural networks is crucial in medical imaging applications where the decision-making depends on the predicted confidence. In this study we propose a calibration procedure for re...

关键词： Neural networks | Decision making | Network architecture | Calibration | Biomedical imaging

摘要：A well known problem in medical imaging is the ability to use an existing model learned on source data, in a new site. This is known as the domain shift problem. We propose a pseudo labels procedure, ...

关键词： Image segmentation | Adaptation models | Magnetic resonance imaging | Semisupervised learning | Data models | Labeling | Task analysis

摘要：Over the past few years, a number of Graph Neural Network (GNN) architectures have been effectively employed for molecular analysis. However, generating annotated molecular data usually requires molec...

关键词： Three-dimensional displays | Quantum chemistry | Perturbation methods | Conferences | Machine learning | Signal processing | Graph neural networks

4008-161-200 800-990-8900

国家科技图书文献中心