Uncertainty in Model-Agnostic Meta-Learning using Variational Inference

27 Jul 2019Cuong NguyenThanh-Toan DoGustavo Carneiro

We introduce a new, rigorously-formulated Bayesian meta-learning algorithm that learns a probability distribution of model parameter prior for few-shot learning. The proposed algorithm employs a gradient-based variational inference to infer the posterior of model parameters to a new task... (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) VAMPIRE Accuracy 51.54 # 29
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) VAMPIRE Accuracy 64.31 # 30
Few-Shot Image Classification OMNIGLOT - 1-Shot, 20-way VAMPIRE Accuracy 93.2 # 15
Few-Shot Image Classification OMNIGLOT - 1-Shot, 5-way VAMPIRE Accuracy 98.43 # 10
Few-Shot Image Classification OMNIGLOT - 5-Shot, 20-way VAMPIRE Accuracy 98.52% # 11
Few-Shot Image Classification OMNIGLOT - 5-Shot, 5-way VAMPIRE Accuracy 99.56% # 9
Few-Shot Image Classification Tiered ImageNet 5-way (1-shot) VAMPIRE Accuracy 69.87 # 4
Few-Shot Image Classification Tiered ImageNet 5-way (5-shot) VAMPIRE Accuracy 82.7 # 6