SOTAVerified

Learning with noisy labels

Learning with noisy labels means When we say "noisy labels," we mean that an adversary has intentionally messed up the labels, which would have come from a "clean" distribution otherwise. This setting can also be used to cast learning from only positive and unlabeled data.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 41–50 of 249 papers

TitleStatusHype
Boosting Co-teaching with Compression Regularization for Label NoiseCode1
Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge DistillationCode1
Compressing Features for Learning with Noisy LabelsCode1
Mitigating Memorization of Noisy Labels via Regularization between RepresentationsCode1
Improving Medical Image Classification in Noisy Labels Using Only Self-supervised PretrainingCode1
Instance-Dependent Noisy Label Learning via Graphical ModellingCode1
Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy LabelsCode1
Active Negative Loss: A Robust Framework for Learning with Noisy LabelsCode1
Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy LabelsCode1
Faster Meta Update Strategy for Noise-Robust Deep LearningCode1
Show:102550
← PrevPage 5 of 25Next →

No leaderboard results yet.