Few-Shot Classification in Unseen Domains by Episodic Meta-Learning Across Visual Domains

TL;DR

This paper introduces a meta-learning framework for few-shot classification that generalizes across unseen domains by leveraging multiple source domains to learn domain-invariant features, improving recognition with limited data.

Contribution

It proposes a novel domain-generalized few-shot learning framework using meta-learning and metric-based mechanisms across multiple source domains.

Findings

Effective in recognizing novel classes in unseen domains.

Learning from small, homogeneous source data can outperform large-scale data.

Insights on backbone model choices for domain-generalized FSL.

Abstract

Few-shot classification aims to carry out classification given only few labeled examples for the categories of interest. Though several approaches have been proposed, most existing few-shot learning (FSL) models assume that base and novel classes are drawn from the same data domain. When it comes to recognizing novel-class data in an unseen domain, this becomes an even more challenging task of domain generalized few-shot classification. In this paper, we present a unique learning framework for domain-generalized few-shot classification, where base classes are from homogeneous multiple source domains, while novel classes to be recognized are from target domains which are not seen during training. By advancing meta-learning strategies, our learning framework exploits data across multiple source domains to capture domain-invariant features, with FSL ability introduced by metric-learning based mechanisms across support and query data. We conduct extensive experiments to verify the effectiveness of our proposed learning framework and show learning from small yet homogeneous source data is able to perform preferably against learning from large-scale one. Moreover, we provide insights into choices of backbone models for domain-generalized few-shot classification.