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 141–150 of 249 papers

TitleStatusHype
Mitigating Memorization of Noisy Labels via Regularization between RepresentationsCode1
Clean or Annotate: How to Spend a Limited Data Collection Budget—0
Relative Instance Credibility Inference for Learning with Noisy Labels—0
Co-variance: Tackling Noisy Labels with Sample Selection by Emphasizing High-variance Examples—0
Can Label-Noise Transition Matrix Help to Improve Sample Selection and Label Correction?—0
Understanding Generalized Label Smoothing when Learning with Noisy LabelsCode1
Chameleon Sampling: Diverse and Pure Example Selection for Online Continual Learning with Noisy Labels—0
Understanding Sharpness-Aware Minimization—0
Robust Temporal Ensembling for Learning with Noisy Labels—0
Learning to Aggregate and Refine Noisy Labels for Visual Sentiment Analysis—0
Show:102550
← PrevPage 15 of 25Next →

No leaderboard results yet.