Výsledky vyhľadávania - Learning with Noisy Labels in Machine Learning

Searching to Exploit Memorization Effect in Deep Learning With Noisy Labels

Autori: Hansi Yang Quanming Yao Bo Han a ďalší

Zdroj: IEEE Transactions on Pattern Analysis and Machine Intelligence. 46:7833-7849

Predmety: Optimization, Nonconvex optimization, Schedules, Noise measurement, Label-noise learning, Training, Deep learning, Semisupervised learning, Automated machine learning (AutoML), Noise, Prediction algorithms

Prístupová URL adresa: https://pubmed.ncbi.nlm.nih.gov/38683712

CLID-MU: Cross-Layer Information Divergence Based Meta Update Strategy for Learning with Noisy Labels

Autori: Ruofan Hu Dongyu Zhang Huayi Zhang a ďalší

Zdroj: Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2. :967-978

Predmety: Machine Learning, FOS: Computer and information sciences, Artificial Intelligence (cs.AI), Artificial Intelligence, Machine Learning (cs.LG)

Prístupová URL adresa: http://arxiv.org/abs/2507.11807

Probabilistic machine learning for noisy labels in Earth observation

Autori: Spyros Kondylatos Nikolaos Ioannis Bountos Ioannis Prapas a ďalší

Zdroj: Scientific Reports, Vol 15, Iss 1, Pp 1-17 (2025)

Predmety: Medicine, Science

Popis súboru: electronic resource

Relation: https://doaj.org/toc/2045-2322

Prístupová URL adresa: https://doaj.org/article/11ab25a32a0b4bc2ae25ffab4be93657

Deep learning with noisy labels in medical prediction problems: a scoping review

Autori: Yishu Wei Yu Deng Cong Sun a ďalší

Zdroj: Journal of the American Medical Informatics Association. 31:1596-1607

Predmety: 0301 basic medicine, FOS: Computer and information sciences, Computer Science - Machine Learning, 03 medical and health sciences, Deep Learning, Biomedical Research, 0302 clinical medicine, Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, Humans, Machine Learning (cs.LG), 3. Good health

Prístupová URL adresa: https://pubmed.ncbi.nlm.nih.gov/38814164
http://arxiv.org/abs/2403.13111

Exploring the Robustness of In-Context Learning with Noisy Labels

Autori: Cheng, Chen Yu, Xinzhi Wen, Haodong a ďalší

Zdroj: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). :1-5

Predmety: FOS: Computer and information sciences, Computer Science - Machine Learning, Computer Science - Computation and Language, Computer Science - Cryptography and Security, Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, Optimization and Control (math.OC), FOS: Mathematics, Mathematics - Optimization and Control, Computation and Language (cs.CL), Cryptography and Security (cs.CR), Machine Learning (cs.LG)

Prístupová URL adresa: http://arxiv.org/abs/2404.18191

Deep Learning With Noisy Labels for Spatiotemporal Drought Detection

Autori: Cortés-Andrés, Jordi Fernández-Torres, Miguel-Ángel Camps-Valls, Gustau a ďalší

Prispievatelia: Cortés-Andrés, Jordi Fernández-Torres, Miguel-Ángel Camps-Valls, Gustau a ďalší

Zdroj: e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Universidad Carlos III de Madrid (UC3M)
IEEE Transactions on Geoscience and Remote Sensing

Predmety: Informática, Noise measurement, Drought detection, Data models, Biological system modeling, Convolutional neural networks (CNNS), Droughts, Predictive models, Europe, Label correction (LC), Noisy labels (NLs), Medio Ambiente, Solid modeling, Training, Three-dimensional displays, Spatiotemporal data, Encoder-decoder architecture, Noise, Hydro-climatological data

Popis súboru: application/pdf

Prístupová URL adresa: https://hdl.handle.net/10016/46966

Probabilistic Machine Learning for Noisy Labels in Earth Observation

Autori: Kondylatos, Spyros Bountos, Nikolaos Ioannis Prapas, Ioannis a ďalší

Predmety: FOS: Computer and information sciences, Computer Science - Machine Learning, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, Machine Learning (cs.LG)

Prístupová URL adresa: http://arxiv.org/abs/2504.03478

Learning from Noisy Labels for Long-Tailed Data via Optimal Transport

Autori: Mengting Li Chuang Zhu

Zdroj: Lecture Notes in Computer Science ISBN: 9789819665938

Predmety: FOS: Computer and information sciences, Computer Science - Machine Learning, Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, Machine Learning (cs.LG)

Prístupová URL adresa: http://arxiv.org/abs/2408.03977

Contrastive prototype federated learning against noisy labels in fetal standard plane detection.

Autori: Fiorentino MC Migliorelli G Villani FP a ďalší

Zdroj: International journal of computer assisted radiology and surgery [Int J Comput Assist Radiol Surg] 2025 Jul; Vol. 20 (7), pp. 1431-1439. Date of Electronic Publication: 2025 May 21.

Spôsob vydávania: Journal Article

Informácie o časopise: Publisher: Springer Country of Publication: Germany NLM ID: 101499225 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1861-6429 (Electronic) Linking ISSN: 18616410 NLM ISO Abbreviation: Int J Comput Assist Radiol Surg Subsets: MEDLINE

Výrazy zo slovníka MeSH: Ultrasonography, Prenatal*/methods , Machine Learning* , Image Interpretation, Computer-Assisted*/methods, Humans ; Pregnancy ; Female ; Federated Learning

A Convergence Path to Deep Learning on Noisy Labels

Autori: Defu Liu Ivor W. Tsang Guowu Yang

Zdroj: IEEE Transactions on Neural Networks and Learning Systems. 35:5170-5182

Prístupová URL adresa: https://pubmed.ncbi.nlm.nih.gov/36136922

SCNet: semi-supervised and contrastive learning against noisy labels with two selection strategy approach.

Autori: Zhu, Dingju Ye, Zhanhao He, Keyi a ďalší

Zdroj: International Journal of General Systems. Oct2025, Vol. 54 Issue 7, p888-901. 14p.

Predmety: *DEEP learning, *IMAGE recognition (Computer vision), *MACHINE learning, *SUPERVISED learning, *FEATURE extraction, *ROBUST statistics

Progressively Robust Loss for Deep Learning with Noisy Labels

Autori: Zhenhuang Cai Shuai Yan Yuanbo Chen a ďalší

Zdroj: 2024 International Joint Conference on Neural Networks (IJCNN). :1-8

Labeling Chaos to Learning Harmony: Federated Learning with Noisy Labels: Federated Learning with Noisy Labels

Autori: Vasileios Tsouvalas Aaqib Saeed Tanir Ozcelebi a ďalší

Zdroj: ACM Transactions on Intelligent Systems and Technology. 15:1-26

Predmety: FOS: Computer and information sciences, Computer Science - Machine Learning, knowledge distillation, label correction, Federated learning, 0202 electrical engineering, electronic engineering, information engineering, deep learning, 02 engineering and technology, 01 natural sciences, noisy labels, 0105 earth and related environmental sciences, Machine Learning (cs.LG)

Prístupová URL adresa: http://arxiv.org/abs/2208.09378

SplitNet: Learnable Clean-Noisy Label Splitting for Learning with Noisy Labels

Autori: Daehwan Kim Kwangrok Ryoo Hansang Cho a ďalší

Zdroj: International Journal of Computer Vision. 133:549-566

Predmety: FOS: Computer and information sciences, 0301 basic medicine, Computer Science - Machine Learning, 03 medical and health sciences, 0302 clinical medicine, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, 0202 electrical engineering, electronic engineering, information engineering, 02 engineering and technology, Machine Learning (cs.LG)

Prístupová URL adresa: http://arxiv.org/abs/2211.11753

An iterative loss correction method for deep learning with noisy labels

Autori: Jiajun Chen Xiaolun Xu Cheng Zheng

Zdroj: Applied and Computational Engineering. 27:90-101

ConfidentMix: Confidence-Guided Mixup for Learning With Noisy Labels

Autori: Ryota Higashimoto Soh Yoshida Mitsuji Muneyasu

Zdroj: IEEE Access, Vol 12, Pp 58519-58531 (2024)

Predmety: semi-supervised learning, Data augmentation, learning with noisy labels, 0202 electrical engineering, electronic engineering, information engineering, deep learning, Electrical engineering. Electronics. Nuclear engineering, 02 engineering and technology, TK1-9971

Prístupová URL adresa: https://doaj.org/article/aa2d6fc03a194480a46540accadfcdf2

Learning with Noisy Labels through Learnable Weighting and Centroid Similarity

Autori: Wani, Farooq Ahmad Bucarelli, Maria Sofia Silvestri, Fabrizio

Zdroj: 2024 International Joint Conference on Neural Networks (IJCNN). :1-9

Predmety: FOS: Computer and information sciences, Computer Science - Machine Learning, Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, Statistics - Machine Learning, Machine Learning (stat.ML), Machine Learning (cs.LG)

Prístupová URL adresa: http://arxiv.org/abs/2303.09470

Deep Learning from Noisy Labels via Robust Nonnegative Matrix Factorization-Based Design

Autori: Daniel Grey Wolnick Shahana Ibrahim Tim Marrinan a ďalší

Zdroj: 2023 IEEE 9th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP). :446-450

Robust Stochastic Neural Ensemble Learning With Noisy Labels for Thoracic Disease Classification

Autori: Hongyu Wang Jiang He Hengfei Cui a ďalší

Zdroj: IEEE Transactions on Medical Imaging. 43:2180-2190

Predmety: Stochastic Processes, Deep Learning, Thoracic Diseases, Databases, Factual, Humans, Radiographic Image Interpretation, Computer-Assisted, Radiography, Thoracic, Neural Networks, Computer, Algorithms

Prístupová URL adresa: https://pubmed.ncbi.nlm.nih.gov/38265913

Compressing Features for Learning With Noisy Labels

Autori: Chen, Yingyi Hu, Shell Xu Shen, Xi a ďalší

Zdroj: IEEE Transactions on Neural Networks and Learning Systems. 35:2124-2138

Predmety: FOS: Computer and information sciences, Technology, Computer Science - Machine Learning, Noise measurement, STADIUS-21-143, Principal component analysis, label noise, Machine Learning (stat.ML), information sorting, 02 engineering and technology, Computer Science, Artificial Intelligence, Machine Learning (cs.LG), Engineering, Computer Science, Theory & Methods, Statistics - Machine Learning, 0202 electrical engineering, electronic engineering, information engineering, Training, Computer Science, Hardware & Architecture, Benchmark testing, Science & Technology, Biological system modeling, deep learning, Engineering, Electrical & Electronic, Deep learning, compression, Kernel, Computer Science, Bias variance decomposition

Prístupová URL adresa: https://pubmed.ncbi.nlm.nih.gov/35802546
http://arxiv.org/abs/2206.13140
https://lirias.kuleuven.be/handle/20.500.12942/701887
https://doi.org/10.1109/tnnls.2022.3186930