Learnable Loss Geometries with Mirror Descent for Scalable and Convergent Meta-Learning
Open paper
Benchmark
Model
Rank
Results
few-shot-image-classification-on-mini-imagenet-5-way-1-shot
MetaMiDA
–
Accuracy: 56.04
few-shot-image-classification-on-mini-imagenet-5-way-5-shot
MetaMiDA
–
Accuracy: 72.06
Rank counts only results with a code link.