4.7 Article

Elucidating robust learning with uncertainty-aware corruption pattern estimation

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Computer Science, Artificial Intelligence

Learning to rectify for robust learning with noisy labels

Haoliang Sun et al.

Summary: The study introduces a new method called Warped Probabilistic Inference (WarPI) for adaptively rectifying the training procedure of a classification network within a meta-learning scenario, aiming to alleviate the negative impact of label noise on the generalization ability of deep models. WarPI outperforms existing approaches and achieves state-of-the-art results on robust learning benchmarks with noisy labels.

PATTERN RECOGNITION (2022)

Article Computer Science, Artificial Intelligence

Towards instance-dependent label noise-tolerant classification: a probabilistic approach

Jakramate Bootkrajang et al.

PATTERN ANALYSIS AND APPLICATIONS (2020)

Article Automation & Control Systems

Semisupervised Robust Modeling of Multimode Industrial Processes for Quality Variable Prediction Based on Student's t Mixture Model

Weiming Shao et al.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2020)

Article Computer Science, Artificial Intelligence

Active cleaning of label noise

Rajmadhan Ekambaram et al.

PATTERN RECOGNITION (2016)

Article Computer Science, Artificial Intelligence

Noise-robust semi-supervised learning via fast sparse coding

Zhiwu Lu et al.

PATTERN RECOGNITION (2015)

Article Computer Science, Artificial Intelligence

Learning kernel logistic regression in the presence of class label noise

Jakramate Bootkrajang et al.

PATTERN RECOGNITION (2014)