Meta-Curvature

NeurIPS 2019 Eunbyung ParkJunier B. Oliva

We propose meta-curvature (MC), a framework to learn curvature information for better generalization and fast model adaptation. MC expands on the model-agnostic meta-learner (MAML) by learning to transform the gradients in the inner optimization such that the transformed gradients achieve better generalization performance to a new task... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) MC2+ Accuracy 55.73 # 30
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) MC2+ Accuracy 70.33 # 30
Few-Shot Image Classification OMNIGLOT - 1-Shot, 20-way MC2+ Accuracy 88% # 17
Few-Shot Image Classification OMNIGLOT - 1-Shot, 5-way MC2+ Accuracy 99.97 # 1
Few-Shot Image Classification OMNIGLOT - 5-Shot, 20-way MC2+ Accuracy 99.65% # 1
Few-Shot Image Classification OMNIGLOT - 5-Shot, 5-way MC2+ Accuracy 99.89 # 3

Methods used in the Paper