Unsupervised Meta-Learning via Latent Space Energy-based Model of Symbol Vector Coupling
Open paper
Benchmark
Model
Rank
Results
unsupervised-few-shot-image-classification-on-mini-imagenet-5-way-1-shot
Meta-SVEBM
–
Accuracy: 43.38
unsupervised-few-shot-image-classification-on-mini-imagenet-5-way-5-shot
Meta-SVEBM
–
Accuracy: 58.03
Rank counts only results with a code link.