Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation
Open paper
Benchmark
Model
Rank
Results
unsupervised-few-shot-image-classification-on-mini-imagenet-5-way-1-shot
AAL
–
Accuracy: 37.67
unsupervised-few-shot-image-classification-on-mini-imagenet-5-way-5-shot
AAL
–
Accuracy: 49.18
Rank counts only results with a code link.