Learning With Noisy Labels On Cifar 10N 1

Accuracy (mean)

평가 결과

이 벤치마크에서 각 모델의 성능 결과

비교 표

모델 이름	Accuracy (mean)
understanding-generalized-label-smoothing	90.29
when-optimizing-f-divergence-is-robust-with-1	89.70
provably-end-to-end-label-noise-learning	88.30
combating-noisy-labels-by-agreement-a-joint	90.30
generative-noisy-label-learning-by-implicit	91.97
190600189	88.33
making-deep-neural-networks-robust-to-label	87.14
making-deep-neural-networks-robust-to-label	86.88
sample-prior-guided-robust-model-learning-to	96.01
how-does-disagreement-help-generalization	89.70
peer-loss-functions-learning-from-noisy	89.06
psscl-a-progressive-sample-selection	96.17
learning-with-instance-dependent-label-noise-1	94.45
co-teaching-robust-training-of-deep-neural	90.33
early-learning-regularization-prevents	91.46
early-learning-regularization-prevents	94.43
generalized-cross-entropy-loss-for-training	87.61
dividemix-learning-with-noisy-labels-as-semi-1	90.18
imprecise-label-learning-a-unified-framework	94.85
does-label-smoothing-mitigate-label-noise	89.80
learning-with-instance-dependent-label-noise-1	89.66
promix-combating-label-noise-via-maximizing	96.97
clusterability-as-an-alternative-to-anchor	90.93
robust-training-under-label-noise-by-over	95.28