Variational Metric Scaling for Metric-Based Meta-Learning

Abstract

Metric-based meta-learning has attracted a lot of attention due to its effectiveness and efficiency in few-shot learning. Recent studies show that metric scaling plays a crucial role in the performance of metric-based meta-learning algorithms. However, there still lacks a principled method for learning the metric scaling parameter automatically. In this paper, we recast metric-based meta-learning from a Bayesian perspective and develop a variational metric scaling framework for learning a proper metric scaling parameter. Firstly, we propose a stochastic variational method to learn a single global scaling parameter. To better fit the embedding space to a given data distribution, we extend our method to learn a dimensional scaling vector to transform the embedding space. Furthermore, to learn task-specific embeddings, we generate task-dependent dimensional scaling vectors with amortized variational inference. Our method is end-to-end without any pre-training and can be used as a simple plug-and-play module for existing metric-based meta-algorithms. Experiments on mini-ImageNet show that our methods can be used to consistently improve the performance of existing metric-based meta-algorithms including prototypical networks and TADAM. The source code can be downloaded from https://github.com/jiaxinchen666/variational-scaling.

arXiv commentAAAI2020

References in corpus (9)

• Distilling the Knowledge in a Neural Network
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• On Calibration of Modern Neural Networks
• A Simple Neural Attentive Meta-Learner
• Aggregating Deep Convolutional Features for Image Retrieval
• Gaussian Prototypical Networks for Few-Shot Learning on Omniglot
• Heated-Up Softmax Embedding
• Large Margin Few-Shot Learning