Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

8-2020

Abstract

Few-shot learning aims to train efficient predictive models with a few examples. The lack of training data leads to poor models that perform high-variance or low-confidence predictions. In this paper, we propose to meta-learn the ensemble of epoch-wise empirical Bayes models (E3BM) to achieve robust predictions. “Epoch-wise'' means that each training epoch has a Bayes model whose parameters are specifically learned and deployed. ”Empirical'' means that the hyperparameters, e.g., used for learning and ensembling the epoch-wise models, are generated by hyperprior learners conditional on task-specific data. We introduce four kinds of hyperprior learners by considering inductive vs. transductive, and epoch-dependent \emph{vs.} epoch-independent, in the paradigm of meta-learning. We conduct extensive experiments for five-class few-shot tasks on three challenging benchmarks: miniImageNet, tieredImageNet, and FC100, and achieve top performance using the epoch-dependent transductive hyperprior learner, which captures the richest information. Our ablation study shows that both “epoch-wise ensemble'' and ”empirical'' encourage high efficiency and robustness in the model performance

Keywords

Confidence predictions, Empirical Bayes, Empirical Bayes models, Hyperparameters, Model performance, Predictive models, Robust predictions, Training epochs

Discipline

Artificial Intelligence and Robotics | Databases and Information Systems

Research Areas

Data Science and Engineering

Publication

Computer Vision - ECCV 2020: 16th European Conference, Glasgow, August 23-28: Proceedings

Volume

12361

First Page

404

Last Page

421

ISBN

9783030585167

Identifier

10.1007/978-3-030-58517-4_24

Publisher

Springer

City or Country

Cham

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1007/978-3-030-58517-4_24

Download

Share

COinS