CMW-Net: an adaptive robust algorithm for sample selection and label correction

Shu, Jun; Yuan, Xiang; Meng, Deyu

doi:10.1093/nsr/nwad084

Cited by 3 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The label noise usually misguides the model training and raises the generalization risk (Frenay and Verleysen 2014). Cleaning noisy data and learning with label noise are critical and challenging in supervised learning and complicated real applications (Wu et al 2020;Shu, Yuan, and Meng 2023).…”

Section: Introductionmentioning

confidence: 99%

Which Is More Effective in Label Noise Cleaning, Correction or Filtering?

Jiang,

Zhang,

Bai

et al. 2024

AAAI

View full text Add to dashboard Cite

Most noise cleaning methods adopt one of the correction and filtering modes to build robust models. However, their effectiveness, applicability, and hyper-parameter insensitivity have not been carefully studied. We compare the two cleaning modes via a rebuilt error bound in noisy environments. At the dataset level, Theorem 5 implies that correction is more effective than filtering when the cleaned datasets have close noise rates. At the sample level, Theorem 6 indicates that confident label noises (large noise probabilities) are more suitable to be corrected, and unconfident noises (medium noise probabilities) should be filtered. Besides, an imperfect hyper-parameter may have fewer negative impacts on filtering than correction. Unlike existing methods with a single cleaning mode, the proposed Fusion cleaning framework of Correction and Filtering (FCF) combines the advantages of different modes to deal with diverse suspicious labels. Experimental results demonstrate that our FCF method can achieve state-of-the-art performance on benchmark datasets.

show abstract

Section: Introductionmentioning

confidence: 99%