Learning With Noisy Labels On Cifar 10N

Accuracy (mean)

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Vergleichstabelle

Modellname	Accuracy (mean)
robust-training-under-label-noise-by-over	95.61
imprecise-label-learning-a-unified-framework	95.47
learning-with-instance-dependent-label-noise-1	95.25
Modell 4	87.77
clusterability-as-an-alternative-to-anchor	91.97
making-deep-neural-networks-robust-to-label	88.24
sample-prior-guided-robust-model-learning-to	96.11
co-teaching-robust-training-of-deep-neural	91.20
early-learning-regularization-prevents	94.83
generative-noisy-label-learning-by-implicit	92.57
when-optimizing-f-divergence-is-robust-with-1	91.64
promix-combating-label-noise-via-maximizing	97.39
early-learning-regularization-prevents	92.38
making-deep-neural-networks-robust-to-label	88.13
peer-loss-functions-learning-from-noisy	90.75
does-label-smoothing-mitigate-label-noise	91.57
generalized-cross-entropy-loss-for-training	87.85
190600189	88.52
combating-noisy-labels-by-agreement-a-joint	91.44
learning-with-instance-dependent-label-noise-1	91.23
understanding-and-improving-early-stopping	94.66
how-does-disagreement-help-generalization	90.61
dividemix-learning-with-noisy-labels-as-semi-1	95.01
psscl-a-progressive-sample-selection	96.41
provably-end-to-end-label-noise-learning	89.70
understanding-generalized-label-smoothing	91.97