Learning with noisy labels
20개 벤치마크 · 논문 269편 · 이 태스크의 논문 보기 →
Benchmarks
CIFAR-10N-Aggregate
CIFAR-10N-Worst
CIFAR-100N
CIFAR-10N-Random1
CIFAR-10N-Random2
CIFAR-10N-Random3
ANIMAL
Clothing1M
Food-101
CIFAR-10N
CIFAR-10
CIFAR-100
COCO-WAN
Chaoyang
mini WebVision 1.0
Most implemented
Sharpness-Aware Minimization for Efficiently Improving Generalization
Protoformer: Embedding Prototypes for Transformers
Open-set Label Noise Can Improve Robustness Against Inherent Label Noise
Normalized Loss Functions for Deep Learning with Noisy Labels
Papers
Holistic Reliability Propagation: Decoupling Annotation and Prediction for Robust Noisy-Label
Learning with noisy labels in multimedia classification often combines external annotations and model predictions into a single reliability weight, even though the two sources can fail for different reasons. We instead e…
Learning with noisy labelsGAMR: Geometric-Aware Manifold Regularization with Virtual Outlier Synthesis for Learning with Noisy Labels
Deep neural networks (DNNs) experience significant performance degradation when processing noisy labels, primarily due to overfitting on mislabeled data. Current mainstream approaches attempt to mitigate this issue by pa…
Learning with noisy labelsWhen Accuracy Is Not Enough: Uncertainty Collapse between Noisy Label Learning and Out-of-Distribution Detection
Learning with noisy labels (LNL) is typically benchmarked by closed-set classification accuracy, yet deployment often requires classifiers to reject out-of-distribution (OOD) inputs. We present a learner-agnostic ACC-OOD…
Out-of-Distribution DetectionLearning with noisy labelsHamBR: Active Decision Boundary Restoration Based on Hamiltonian Dynamics for Learning with Noisy Labels
In large-scale visual recognition and data mining tasks, the presence of noisy labels severely undermines the generalization capability of deep neural networks (DNNs). Prevalent sample selection methods rely primarily on…
Learning with noisy labelsConformal Margin Risk Minimization: An Envelope Framework for Robust Learning under Label Noise
Most methods for learning with noisy labels require privileged knowledge such as noise transition matrices, clean subsets or pretrained feature extractors, resources typically unavailable when robustness is most needed. …
Learning with noisy labelsVariational Rectification Inference for Learning with Noisy Labels
Label noise has been broadly observed in real-world datasets. To mitigate the negative impact of overfitting to label noise for deep models, effective strategies (\textit{e.g.}, re-weighting, or loss rectification) have …
Learning with noisy labels