Domain-Agnostic Few-Shot Classification by Learning Disparate Modulators

TL;DR

This paper introduces a domain-agnostic few-shot classification method that uses a pool of models with shared base networks and distinct modulators, enabling effective learning across multiple and unseen domains.

Contribution

It proposes a novel cross-domain meta-learning framework with a model pool and disparate modulators, enhancing few-shot classification across diverse and unseen domains.

Findings

Effective across multiple diverse datasets

Improves generalization to unseen domains

Maintains domain-invariant features

Abstract

Although few-shot learning research has advanced rapidly with the help of meta-learning, its practical usefulness is still limited because most of them assumed that all meta-training and meta-testing examples came from a single domain. We propose a simple but effective way for few-shot classification in which a task distribution spans multiple domains including ones never seen during meta-training. The key idea is to build a pool of models to cover this wide task distribution and learn to select the best one for a particular task through cross-domain meta-learning. All models in the pool share a base network while each model has a separate modulator to refine the base network in its own way. This framework allows the pool to have representational diversity without losing beneficial domain-invariant features. We verify the effectiveness of the proposed algorithm through experiments on various datasets across diverse domains.