Improved transferability of self-supervised learning models through batch normalization finetuning

Open paper
Benchmark Model Rank Results
classification-on-mhistMoCo-v2 (ResNet-50)#1Accuracy: 88.03
classification-on-mhistBarlow Twins (ResNet-50)#3Accuracy: 84.03
classification-on-mhistSwAV (ResNet-50)#4Accuracy: 83.21

Rank counts only results with a code link.