In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning

Open paper
Benchmark Model Rank Results
semi-supervised-image-classification-on-cifarUPS (Shake-Shake)#12Percentage error: 4.86
semi-supervised-image-classification-on-cifarUPS (CNN-13)#24Percentage error: 6.39±0.02
semi-supervised-image-classification-on-cifar-11UPS (CNN-13)#2Accuracy: 91.82
semi-supervised-image-classification-on-cifar-2UPS (CNN-13)#16Percentage error: 32
semi-supervised-medical-image-classification-1UPS#3AUC: 65.51

Rank counts only results with a code link.