Contrastive Learning Improves Model Robustness Under Label Noise

Open paper
Benchmark Model Rank Results
image-classification-on-clothing1mMAE (SimCLR)#26Accuracy: 73.36%
image-classification-on-clothing1mGeneralized CE (SimCLR)#27Accuracy: 73.35%
image-classification-on-clothing1mCCE (SimCLR)#29Accuracy: 73.27%

Rank counts only results with a code link.