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

by   Yudong Chen, et al.
Tsinghua University

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[], demonstrating the advantages of our proposed system. The codes are publicly available at


page 1

page 2

page 3

page 4


Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?

The focus of recent meta-learning research has been on the development o...

CMVAE: Causal Meta VAE for Unsupervised Meta-Learning

Unsupervised meta-learning aims to learn the meta knowledge from unlabel...

Classical Sequence Match is a Competitive Few-Shot One-Class Learner

Nowadays, transformer-based models gradually become the default choice f...

Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning Approach

Few-shot learning is a challenging problem that has attracted more and m...

MetaHDR: Model-Agnostic Meta-Learning for HDR Image Reconstruction

Capturing scenes with a high dynamic range is crucial to reproducing ima...

Multi-Modal Fusion by Meta-Initialization

When experience is scarce, models may have insufficient information to a...

Layer-Wise Adaptive Updating for Few-Shot Image Classification

Few-shot image classification (FSIC), which requires a model to recogniz...

Please sign up or login with your details

Forgot password? Click here to reset