MetaDelta: A Meta-Learning System for Few-shot Image Classification

TL;DR

MetaDelta is a practical meta-learning system designed for few-shot image classification, emphasizing efficiency and generalization through multiple meta-learners supervised by a central controller and a meta-ensemble module.

Contribution

It introduces a novel meta-learning system with multiple meta-learners and a meta-ensemble for improved efficiency and generalization in few-shot learning.

Findings

Ranked first in AAAI 2021 MetaDL Challenge

Demonstrated superior generalization on unseen datasets

Efficient training with multiple meta-learners

Abstract

Meta-learning aims at learning quickly on novel tasks with limited data by transferring generic experience learned from previous tasks. Naturally, few-shot learning has been one of the most popular applications for meta-learning. However, existing meta-learning algorithms rarely consider the time and resource efficiency or the generalization capacity for unknown datasets, which limits their applicability in real-world scenarios. In this paper, we propose MetaDelta, a novel practical meta-learning system for the few-shot image classification. MetaDelta consists of two core components: i) multiple meta-learners supervised by a central controller to ensure efficiency, and ii) a meta-ensemble module in charge of integrated inference and better generalization. In particular, each meta-learner in MetaDelta is composed of a unique pretrained encoder fine-tuned by batch training and parameter-free decoder used for prediction. MetaDelta ranks first in the final phase in the AAAI 2021 MetaDL Challenge\footnote{https://competitions.codalab.org/competitions/26638}, demonstrating the advantages of our proposed system. The codes are publicly available at https://github.com/Frozenmad/MetaDelta.