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
Robust Training under Label Noise by Over-parameterizationCode1
L2B: Learning to Bootstrap Robust Models for Combating Label NoiseCode1
Hard Sample Aware Noise Robust Learning for Histopathology Image ClassificationCode1
Sample Prior Guided Robust Model Learning to Suppress Noisy LabelsCode1
Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label MiscorrectionCode1
SSR: An Efficient and Robust Framework for Learning with Unknown Label NoiseCode1
Learning with Noisy Labels Revisited: A Study Using Real-World Human AnnotationsCode1
Mitigating Memorization of Noisy Labels via Regularization between RepresentationsCode1
Understanding Generalized Label Smoothing when Learning with Noisy LabelsCode1
Co-Correcting: Noise-tolerant Medical Image Classification via mutual Label CorrectionCode1
Show:102550
← PrevPage 5 of 25Next →

No leaderboard results yet.