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 101–125 of 249 papers

TitleStatusHype
Learning with Open-world Noisy Data via Class-independent Margin in Dual Representation SpaceCode0
PLReMix: Combating Noisy Labels with Pseudo-Label Relaxed Contrastive Representation LearningCode0
Partial Label Supervision for Agnostic Generative Noisy Label LearningCode0
No Regret Sample Selection with Noisy LabelsCode0
Confident Learning: Estimating Uncertainty in Dataset LabelsCode0
Probabilistic End-to-end Noise Correction for Learning with Noisy LabelsCode0
ANNE: Adaptive Nearest Neighbors and Eigenvector-based Sample Selection for Robust Learning with Noisy LabelsCode0
Active Label Refinement for Robust Training of Imbalanced Medical Image Classification Tasks in the Presence of High Label NoiseCode0
Learning advisor networks for noisy image classificationCode0
Cross-to-merge training with class balance strategy for learning with noisy labelsCode0
PropMix: Hard Sample Filtering and Proportional MixUp for Learning with Noisy LabelsCode0
Symmetric Cross Entropy for Robust Learning with Noisy LabelsCode0
Debiased Sample Selection for Combating Noisy LabelsCode0
Learning with Noisy Labels by Adaptive Gradient-Based Outlier RemovalCode0
LNL+K: Enhancing Learning with Noisy Labels Through Noise Source Knowledge IntegrationCode0
LongReMix: Robust Learning with High Confidence Samples in a Noisy Label EnvironmentCode0
Making Deep Neural Networks Robust to Label Noise: a Loss Correction ApproachCode0
SELFIE: Refurbishing Unclean Samples for Robust Deep LearningCode0
Detect and Correct: A Selective Noise Correction Method for Learning with Noisy LabelsCode0
Dimensionality-Driven Learning with Noisy LabelsCode0
Are Anchor Points Really Indispensable in Label-Noise Learning?Code0
Rethinking Noisy Label Learning in Real-world Annotation Scenarios from the Noise-type PerspectiveCode0
PSSCL: A progressive sample selection framework with contrastive loss designed for noisy labelsCode0
A Unified Framework for Connecting Noise Modeling to Boost Noise DetectionCode0
SIGUA: Forgetting May Make Learning with Noisy Labels More RobustCode0
Show:102550
← PrevPage 5 of 10Next →

No leaderboard results yet.