Learning With Noisy Labels On Cifar 10N Worst

Accuracy (mean)

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Vergleichstabelle

Modellname	Accuracy (mean)
co-teaching-robust-training-of-deep-neural	83.83
early-learning-regularization-prevents	83.58
generative-noisy-label-learning-by-implicit	86.99
190600189	80.48
combating-noisy-labels-by-agreement-a-joint	83.37
psscl-a-progressive-sample-selection	95.12
sample-prior-guided-robust-model-learning-to	93.65
Modell 8	77.69
understanding-generalized-label-smoothing-1	82.99
making-deep-neural-networks-robust-to-label	79.79
how-does-disagreement-help-generalization	83.26
when-optimizing-f-divergence-is-robust-with-1	82.53
promix-combating-label-noise-via-maximizing	96.16
generalized-cross-entropy-loss-for-training	80.66
dividemix-learning-with-noisy-labels-as-semi-1	92.56
clusterability-as-an-alternative-to-anchor	85.36
provably-end-to-end-label-noise-learning	80.53
learning-with-instance-dependent-label-noise-1	83.60
early-learning-regularization-prevents	91.09
peer-loss-functions-learning-from-noisy	82.53
robust-training-under-label-noise-by-over	93.24
does-label-smoothing-mitigate-label-noise	82.76
making-deep-neural-networks-robust-to-label	77.61
learning-with-instance-dependent-label-noise-1	91.66
imprecise-label-learning-a-unified-framework	93.58