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 151–175 of 249 papers

TitleStatusHype
Co-Correcting: Noise-tolerant Medical Image Classification via mutual Label CorrectionCode1
Confidence Adaptive Regularization for Deep Learning with Noisy Labels—0
Cooperative Learning for Noisy Supervision—0
Co-learning: Learning from Noisy Labels with Self-supervisionCode1
Learning with Noisy Labels via Sparse RegularizationCode1
Learning with Noisy Labels for Robust Point Cloud SegmentationCode1
An Instance-Dependent Simulation Framework for Learning with Label Noise—0
Can Less be More? When Increasing-to-Balancing Label Noise Rates Considered BeneficialCode0
Mitigating Memorization in Sample Selection for Learning with Noisy Labels—0
Understanding and Improving Early Stopping for Learning with Noisy LabelsCode1
Distilling effective supervision for robust medical image segmentation with noisy labels—0
Open-set Label Noise Can Improve Robustness Against Inherent Label NoiseCode1
DAT: Training Deep Networks Robust To Label-Noise by Matching the Feature DistributionsCode1
DualGraph: A Graph-Based Method for Reasoning About Label Noise—0
Influential Rank: A New Perspective of Post-training for Robust Model against Noisy Labels—0
To Smooth or Not? When Label Smoothing Meets Noisy LabelsCode1
Asymmetric Loss Functions for Learning with Noisy LabelsCode1
Sample Selection with Uncertainty of Losses for Learning with Noisy Labels—0
Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge DistillationCode1
Joint Text and Label Generation for Spoken Language Understanding—0
Generalized Jensen-Shannon Divergence Loss for Learning with Noisy LabelsCode1
Faster Meta Update Strategy for Noise-Robust Deep LearningCode1
Boosting Co-teaching with Compression Regularization for Label NoiseCode1
MultiScene: A Large-scale Dataset and Benchmark for Multi-scene Recognition in Single Aerial ImagesCode1
Transform consistency for learning with noisy labels—0
Show:102550
← PrevPage 7 of 10Next →

No leaderboard results yet.