paper-with-me

Learning with noisy labels

20개 벤치마크 · 논문 269편 · 이 태스크의 논문 보기 →

Benchmarks

CIFAR-10N-Aggregate

결과 52개

CIFAR-10N-Worst

결과 50개

CIFAR-100N

결과 49개

CIFAR-10N-Random1

결과 48개

CIFAR-10N-Random2

결과 46개

CIFAR-10N-Random3

결과 46개

ANIMAL

결과 38개

Clothing1M

결과 10개

Food-101

결과 6개

CIFAR-10N

결과 3개

CIFAR-10

결과 2개

CIFAR-100

결과 2개

COCO-WAN

결과 2개

Chaoyang

결과 2개

mini WebVision 1.0

결과 2개

Most implemented

Papers

Holistic Reliability Propagation: Decoupling Annotation and Prediction for Robust Noisy-Label

2026-05-20 · Jingyang Mao, Ningkang Peng, Yanhui Gu arxiv

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 labels

GAMR: Geometric-Aware Manifold Regularization with Virtual Outlier Synthesis for Learning with Noisy Labels

2026-05-20 · Ningkang Peng, Jingyang Mao, Xiaoqian Peng, Peirong Ma 외 arxiv

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 labels

When Accuracy Is Not Enough: Uncertainty Collapse between Noisy Label Learning and Out-of-Distribution Detection

2026-05-18 · Ningkang Peng, Jingyang Mao, Runhan Zhou, Peirong Ma 외 arxiv

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 labels

HamBR: Active Decision Boundary Restoration Based on Hamiltonian Dynamics for Learning with Noisy Labels

2026-05-12 · Ningkang Peng, Jingyang Mao, Qianfeng Yu, Xiaoqian Peng 외 arxiv

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 labels

Conformal Margin Risk Minimization: An Envelope Framework for Robust Learning under Label Noise

2026-04-07 · Yuanjie Shi, Peihong Li, Zijian Zhang, Janardhan Rao Doppa 외 arxiv

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 labels

Variational Rectification Inference for Learning with Noisy Labels

2026-03-18 · Haoliang Sun, Qi Wei, Lei Feng, Yupeng Hu 외 arxiv

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

전체 269편 보기 →