IPCL: Iterative Pseudo-Supervised Contrastive Learning to Improve Self-Supervised Feature Representation

Benchmark Model Rank Results
unsupervised-image-classification-on-cifar-10IPCL (ResNet18)#8Accuracy: 88.81
unsupervised-image-classification-on-stl-10IPCL (ResNet18)#8Accuracy: 80.91