Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples

Open paper
Benchmark Model Rank Results
semi-supervised-image-classification-on-cifar-10-4000-labelsPAWS-NN (WRN-28-2)#4Percentage error: 4.0 ± 0.25
semi-supervised-image-classification-on-imagenet-10-labeled-dataPAWS (ResNet-50 4x)#11Top 1 Accuracy: 79.0%
semi-supervised-image-classification-on-imagenet-10-labeled-dataPAWS (ResNet-50 2x)#14Top 1 Accuracy: 77.8%
semi-supervised-image-classification-on-imagenet-10-labeled-dataPAWS (ResNet-50)#19Top 1 Accuracy: 75.5%
semi-supervised-image-classification-on-imagenet-1-labeled-dataPAWS (ResNet-50 4x)#16Top 1 Accuracy: 69.9%
semi-supervised-image-classification-on-imagenet-1-labeled-dataPAWS (ResNet-50 2x)#17Top 1 Accuracy: 69.6%
semi-supervised-image-classification-on-imagenet-1-labeled-dataPAWS (ResNet-50)#24Top 1 Accuracy: 66.5%
image-classification-on-imagenetPAWS (ResNet-50, 10% labels)#987Top 1 Accuracy: 75.5%
image-classification-on-imagenetPAWS (ResNet-50, 1% labels)#1093Top 1 Accuracy: 66.5%

Rank counts only results with a code link.