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 21–30 of 249 papers

TitleStatusHype
Clusterability as an Alternative to Anchor Points When Learning with Noisy LabelsCode1
Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label LearningCode1
Active Negative Loss: A Robust Framework for Learning with Noisy LabelsCode1
Combating noisy labels by agreement: A joint training method with co-regularizationCode1
Co-learning: Learning from Noisy Labels with Self-supervisionCode1
Co-Learning Meets Stitch-Up for Noisy Multi-label Visual RecognitionCode1
Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge DistillationCode1
Compressing Features for Learning with Noisy LabelsCode1
CLIPCleaner: Cleaning Noisy Labels with CLIPCode1
Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy LabelsCode1
Show:102550
← PrevPage 3 of 25Next →

No leaderboard results yet.