SMU Research Data Repository (RDR)
Download file
Download file
Download file
Download file
Download file
5 files

Data from: An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning

posted on 2022-09-28, 02:54 authored by Yaoyao LIU, Bernt SCHIELE, Qianru SUNQianru SUN

PyTorch implementation of "An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning"

This repository contains the PyTorch implementation for the ECCV 2020 Paper "An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning".


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 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.


Confidential or personally identifiable information

  • I confirm that the uploaded data has no confidential or personally identifiable information.

Usage metrics

    School of Computing and Information Systems