IPCL (ResNet18)

Reported on 4 benchmarks across 2 tasks

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision2 results

Image ClassificationonSTL-10
Accuracy
80.91
Image ClassificationonCIFAR-10
Accuracy
88.81

Methodology2 results

Contrastive LearningonCIFAR-10
Accuracy (Top-1)
84.77
Contrastive LearningonSTL-10
Accuracy (Top-1)
85.55