Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace

ICML 2018 Yoonho LeeSeungjin Choi

Gradient-based meta-learning methods leverage gradient descent to learn the commonalities among various tasks. While previous such methods have been successful in meta-learning tasks, they resort to simple gradient descent during meta-testing... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) MT-Net Accuracy 51.7 # 33
Few-Shot Image Classification OMNIGLOT - 1-Shot, 20-way MT-net Accuracy 96.2% # 8
Few-Shot Image Classification OMNIGLOT - 1-Shot, 5-way MT-net Accuracy 99.5 # 5

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet