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 71–80 of 249 papers

TitleStatusHype
Towards Robustness to Label Noise in Text Classification via Noise ModelingCode1
Robustness of Accuracy Metric and its Inspirations in Learning with Noisy LabelsCode1
Robust Federated Learning with Noisy LabelsCode1
When Optimizing f-divergence is Robust with Label NoiseCode1
Learning with Instance-Dependent Label Noise: A Sample Sieve ApproachCode1
Early-Learning Regularization Prevents Memorization of Noisy LabelsCode1
Normalized Loss Functions for Deep Learning with Noisy LabelsCode1
Combating noisy labels by agreement: A joint training method with co-regularizationCode1
Improving Generalization by Controlling Label-Noise Information in Neural Network WeightsCode1
DivideMix: Learning with Noisy Labels as Semi-supervised LearningCode1
Show:102550
← PrevPage 8 of 25Next →

No leaderboard results yet.