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
Labeling Chaos to Learning Harmony: Federated Learning with Noisy LabelsCode0
Neighborhood Collective Estimation for Noisy Label Identification and CorrectionCode1
Jigsaw-ViT: Learning Jigsaw Puzzles in Vision TransformerCode1
Learn From All: Erasing Attention Consistency for Noisy Label Facial Expression RecognitionCode1
ProMix: Combating Label Noise via Maximizing Clean Sample UtilityCode1
Compressing Features for Learning with Noisy LabelsCode1
Towards Harnessing Feature Embedding for Robust Learning with Noisy Labels—0
Protoformer: Embedding Prototypes for TransformersCode1
Joint Class-Affinity Loss Correction for Robust Medical Image Segmentation with Noisy LabelsCode1
To Aggregate or Not? Learning with Separate Noisy Labels—0
Communication-Efficient Robust Federated Learning with Noisy Labels—0
Task-Adaptive Pre-Training for Boosting Learning With Noisy Labels: A Study on Text Classification for African Languages—0
FedNoiL: A Simple Two-Level Sampling Method for Federated Learning with Noisy Labels—0
SELC: Self-Ensemble Label Correction Improves Learning with Noisy LabelsCode1
From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative ModelCode1
Reliable Label Correction is a Good Booster When Learning with Extremely Noisy LabelsCode1
Is BERT Robust to Label Noise? A Study on Learning with Noisy Labels in Text ClassificationCode1
Few-shot Learning with Noisy LabelsCode1
UNICON: Combating Label Noise Through Uniform Selection and Contrastive LearningCode1
Scalable Penalized Regression for Noise Detection in Learning with Noisy LabelsCode1
Selective-Supervised Contrastive Learning with Noisy LabelsCode1
On Learning Contrastive Representations for Learning with Noisy LabelsCode1
Robust Training under Label Noise by Over-parameterizationCode1
PENCIL: Deep Learning with Noisy Labels—0
L2B: Learning to Bootstrap Robust Models for Combating Label NoiseCode1
Show:102550
← PrevPage 5 of 10Next →

No leaderboard results yet.