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 201–249 of 249 papers

TitleStatusHype
Rethinking Noisy Label Learning in Real-world Annotation Scenarios from the Noise-type PerspectiveCode0
Meta Label Correction for Noisy Label LearningCode0
PropMix: Hard Sample Filtering and Proportional MixUp for Learning with Noisy LabelsCode0
MILD: Modeling the Instance Learning Dynamics for Learning with Noisy LabelsCode0
Symmetric Cross Entropy for Robust Learning with Noisy LabelsCode0
Mitigating Label Noise on Graph via Topological Sample SelectionCode0
Learning to Detect and Retrieve Objects from Unlabeled VideosCode0
Robust Loss Functions for Training Decision Trees with Noisy LabelsCode0
Debiased Sample Selection for Combating Noisy LabelsCode0
Joint Optimization Framework for Learning with Noisy LabelsCode0
Model and Data Agreement for Learning with Noisy LabelsCode0
Exploring Parity Challenges in Reinforcement Learning through Curriculum Learning with Noisy LabelsCode0
Unsupervised Domain Adaptation of Black-Box Source ModelsCode0
CoLafier: Collaborative Noisy Label Purifier With Local Intrinsic Dimensionality GuidanceCode0
Exploring the Robustness of In-Context Learning with Noisy LabelsCode0
Latent Class-Conditional Noise ModelCode0
Late Stopping: Avoiding Confidently Learning from Mislabeled ExamplesCode0
L_DMI: An Information-theoretic Noise-robust Loss FunctionCode0
Exploring Video-Based Driver Activity Recognition under Noisy LabelsCode0
Dynamic Loss For Robust LearningCode0
Labeling Chaos to Learning Harmony: Federated Learning with Noisy LabelsCode0
Learning advisor networks for noisy image classificationCode0
Detect and Correct: A Selective Noise Correction Method for Learning with Noisy LabelsCode0
NoisywikiHow: A Benchmark for Learning with Real-world Noisy Labels in Natural Language ProcessingCode0
Dimensionality-Driven Learning with Noisy LabelsCode0
Learning with Noisy Labels through Learnable Weighting and Centroid SimilarityCode0
Learning to Learn from Noisy Labeled DataCode0
Learning to Rectify for Robust Learning with Noisy LabelsCode0
No Regret Sample Selection with Noisy LabelsCode0
ANNE: Adaptive Nearest Neighbors and Eigenvector-based Sample Selection for Robust Learning with Noisy LabelsCode0
An Instance-Dependent Simulation Framework for Learning with Label NoiseCode0
Safeguarded Dynamic Label Regression for Generalized Noisy SupervisionCode0
Are Anchor Points Really Indispensable in Label-Noise Learning?Code0
Learning with Neighbor Consistency for Noisy LabelsCode0
Early Stopping Against Label Noise Without Validation DataCode0
PLReMix: Combating Noisy Labels with Pseudo-Label Relaxed Contrastive Representation LearningCode0
Learning with Noisy Labels by Adaptive Gradient-Based Outlier RemovalCode0
PSSCL: A progressive sample selection framework with contrastive loss designed for noisy labelsCode0
SELFIE: Refurbishing Unclean Samples for Robust Deep LearningCode0
Enhanced Meta Label Correction for Coping with Label CorruptionCode0
A Unified Framework for Connecting Noise Modeling to Boost Noise DetectionCode0
Confident Learning: Estimating Uncertainty in Dataset LabelsCode0
Benchmarking Label Noise in Instance Segmentation: Spatial Noise MattersCode0
Blind Knowledge Distillation for Robust Image ClassificationCode0
Probabilistic End-to-end Noise Correction for Learning with Noisy LabelsCode0
Bootstrapping the Relationship Between Images and Their Clean and Noisy LabelsCode0
SIGUA: Forgetting May Make Learning with Noisy Labels More RobustCode0
Can Less be More? When Increasing-to-Balancing Label Noise Rates Considered BeneficialCode0
Can We Treat Noisy Labels as Accurate?Code0
Show:102550
← PrevPage 5 of 5Next →

No leaderboard results yet.