Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning

Benchmark Model Rank Results
unsupervised-few-shot-image-classification-on-tiered-imagenet-5-way-1-shotPL-CFE#5Accuracy: 49.51
unsupervised-few-shot-image-classification-on-tiered-imagenet-5-way-5-shotPL-CFE#6Accuracy: 64.31
unsupervised-few-shot-image-classification-on-mini-imagenet-5-way-1-shotPL-CFE#7Accuracy: 49.13
unsupervised-few-shot-image-classification-on-mini-imagenet-5-way-5-shotPL-CFE#11Accuracy: 62.91