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 51–75 of 249 papers

TitleStatusHype
Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label ConfigurationsCode1
CSOT: Curriculum and Structure-Aware Optimal Transport for Learning with Noisy LabelsCode1
DAT: Training Deep Networks Robust To Label-Noise by Matching the Feature DistributionsCode1
Provably End-to-end Label-Noise Learning without Anchor PointsCode1
Robustness of Accuracy Metric and its Inspirations in Learning with Noisy LabelsCode1
Robust Training under Label Noise by Over-parameterizationCode1
SSR: An Efficient and Robust Framework for Learning with Unknown Label NoiseCode1
Sample Prior Guided Robust Model Learning to Suppress Noisy LabelsCode1
Mitigating Memorization of Noisy Labels via Regularization between RepresentationsCode1
CLIPCleaner: Cleaning Noisy Labels with CLIPCode1
Clusterability as an Alternative to Anchor Points When Learning with Noisy LabelsCode1
Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label LearningCode1
Learning with Noisy labels via Self-supervised Adversarial Noisy MaskingCode1
DISC: Learning From Noisy Labels via Dynamic Instance-Specific Selection and CorrectionCode1
Augmentation Strategies for Learning with Noisy LabelsCode1
DivideMix: Learning with Noisy Labels as Semi-supervised LearningCode1
AlleNoise: large-scale text classification benchmark dataset with real-world label noiseCode1
Jigsaw-ViT: Learning Jigsaw Puzzles in Vision TransformerCode1
Co-learning: Learning from Noisy Labels with Self-supervisionCode1
Knockoffs-SPR: Clean Sample Selection in Learning with Noisy LabelsCode1
Co-Learning Meets Stitch-Up for Noisy Multi-label Visual RecognitionCode1
Early-Learning Regularization Prevents Memorization of Noisy LabelsCode1
Collaborative Noisy Label Cleaner: Learning Scene-aware Trailers for Multi-modal Highlight Detection in MoviesCode1
FedNoisy: Federated Noisy Label Learning BenchmarkCode1
Open-set Label Noise Can Improve Robustness Against Inherent Label NoiseCode1
Show:102550
← PrevPage 3 of 10Next →

No leaderboard results yet.