Uncertainty in Model-Agnostic Meta-Learning using Variational Inference
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. Our algorithm can be applied to any model architecture and can be implemented in various machine learning paradigms, including regression and classification. We show that the models trained with our proposed meta-learning algorithm are well calibrated and accurate, with state-of-the-art calibration and classification results on two few-shot classification benchmarks (Omniglot and Mini-ImageNet), and competitive results in a multi-modal task-distribution regression.
Code (1)
Tasks
BIG-bench Machine LearningClassificationFew-Shot Image ClassificationFew-Shot LearningGeneral ClassificationMeta-LearningregressionVariational InferenceSimilar Papers 제목 키워드 기반
Bayesian Model-Agnostic Meta-Learning
Learning to infer Bayesian posterior from a few-shot dataset is an important step towards robust meta-learning due to the model uncertainty inherent in the problem. In this paper, we propose a novel Bayesian model-agnost…
Active Learningimage-classificationImage ClassificationMeta-Learning+3Meta-Learning Bayesian Neural Network Priors Based on PAC-Bayesian Theory
Bayesian deep learning is a promising approach towards improved uncertainty quantification and sample efficiency. Due to their complex parameter space, choosing informative priors for Bayesian Neural Networks (BNNs) is c…
Meta-LearningUncertainty QuantificationVariational InferenceMeta-Learning with Shared Amortized Variational Inference
We propose a novel amortized variational inference scheme for an empirical Bayes meta-learning model, where model parameters are treated as latent variables. We learn the prior distribution over model parameters conditio…
Meta-LearningVariational InferenceGradient-Based Quantification of Epistemic Uncertainty for Deep Object Detectors
The vast majority of uncertainty quantification methods for deep object detectors such as variational inference are based on the network output. Here, we study gradient-based epistemic uncertainty metrics for deep object…
Objectobject-detectionObject DetectionUncertainty Quantification+1Probabilistic task modelling for meta-learning
We propose probabilistic task modelling -- a generative probabilistic model for collections of tasks used in meta-learning. The proposed model combines variational auto-encoding and latent Dirichlet allocation to model e…
Meta-Learningparameter estimationVariational Inference