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 111–120 of 249 papers

TitleStatusHype
LaplaceConfidence: a Graph-based Approach for Learning with Noisy Labels—0
Combining Self-Supervised and Supervised Learning with Noisy Labels—0
Deep learning with noisy labels: exploring techniques and remedies in medical image analysis—0
ALEX: Towards Effective Graph Transfer Learning with Noisy Labels—0
L_DMI: A Novel Information-theoretic Loss Function for Training Deep Nets Robust to Label Noise—0
Can Label-Noise Transition Matrix Help to Improve Sample Selection and Label Correction?—0
Learning Adaptive Loss for Robust Learning with Noisy Labels—0
Deep Self-Learning From Noisy Labels—0
High-dimensional Learning with Noisy Labels—0
Learning with Noisy Labels for Sentence-level Sentiment Classification—0
Show:102550
← PrevPage 12 of 25Next →

No leaderboard results yet.