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

Showing 226249 of 249 papers

TitleStatusHype
O2U-Net: A Simple Noisy Label Detection Approach for Deep Neural Networks0
A Simple yet Effective Baseline for Robust Deep Learning with Noisy Labels0
L_DMI: An Information-theoretic Noise-robust Loss FunctionCode0
Learning with Noisy Labels for Sentence-level Sentiment Classification0
Symmetric Cross Entropy for Robust Learning with Noisy LabelsCode0
Deep Self-Learning From Noisy Labels0
SELFIE: Refurbishing Unclean Samples for Robust Deep LearningCode0
Are Anchor Points Really Indispensable in Label-Noise Learning?Code0
Learning to Detect and Retrieve Objects from Unlabeled VideosCode0
A Simple yet Effective Baseline for Robust Deep Learning with Noisy Labels0
Unifying semi-supervised and robust learning by mixup0
Probabilistic End-to-end Noise Correction for Learning with Noisy LabelsCode0
Safeguarded Dynamic Label Regression for Generalized Noisy SupervisionCode0
How does Disagreement Help Generalization against Label Corruption?Code0
Learning to Learn from Noisy Labeled DataCode0
Limited Gradient Descent: Learning With Noisy Labels0
SIGUA: Forgetting May Make Learning with Noisy Labels More RobustCode0
Randomized Wagering Mechanisms0
Dimensionality-Driven Learning with Noisy LabelsCode0
Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy LabelsCode1
Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy LabelsCode1
Joint Optimization Framework for Learning with Noisy LabelsCode0
Making Deep Neural Networks Robust to Label Noise: a Loss Correction ApproachCode0
Learning with Noisy Labels0
Show:102550
← PrevPage 10 of 10Next →

No leaderboard results yet.