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

arXiv: https://arxiv.org/abs/2102.10744 · HTML: https://mlsanity.com/paper/2102.10744/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 24 references that are in the map.
- First posted on arXiv 22 Feb 2021.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Meta-Learning with Latent Embedding Optimization](https://mlsanity.com/paper/1807.05960/) (2018)
- [Meta-Learning for Semi-Supervised Few-Shot Classification](https://mlsanity.com/paper/1803.00676/) (2018)
- [Domain Generalization by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1903.06864/) (2019)
- [Meta Networks](https://mlsanity.com/paper/1703.00837/) (2017)
- [Meta-Learning: A Survey](https://mlsanity.com/paper/1810.03548/) (2018)
- [Episodic Training for Domain Generalization](https://mlsanity.com/paper/1902.00113/) (2019)
- [Self-Supervised GANs via Auxiliary Rotation Loss](https://mlsanity.com/paper/1811.11212/) (2018)
- [Laplacian Regularized Few-Shot Learning](https://mlsanity.com/paper/2006.15486/) (2020)
- [Embedding Propagation: Smoother Manifold for Few-Shot Classification](https://mlsanity.com/paper/2003.04151/) (2020)
- [Meta-Curvature](https://mlsanity.com/paper/1902.03356/) (2019)
- [Meta-Learned Confidence for Few-shot Learning](https://mlsanity.com/paper/2002.12017/) (2020)

## Built on by (most cited first, 10 of 10)

- [Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification](https://mlsanity.com/paper/2206.08138/) (2022)
- [MetaNOR: A Meta-Learnt Nonlocal Operator Regression Approach for Metamaterial Modeling](https://mlsanity.com/paper/2206.02040/) (2022)
- [PMFL: Partial Meta-Federated Learning for heterogeneous tasks and its applications on real-world medical records](https://mlsanity.com/paper/2112.05321/) (2021)
- [Advances in MetaDL: AAAI 2021 challenge and workshop](https://mlsanity.com/paper/2202.01890/) (2022)
- [NeurIPS'22 Cross-Domain MetaDL competition: Design and baseline results](https://mlsanity.com/paper/2208.14686/) (2022)
- [Contrastive Meta-Learning for Partially Observable Few-Shot Learning](https://mlsanity.com/paper/2301.13136/) (2023)
- [Rethinking Meta-Learning from a Learning Lens](https://mlsanity.com/paper/2409.08474/) (2024)
- [Meta-Prior: Meta learning for Adaptive Inverse Problem Solvers](https://mlsanity.com/paper/2311.18710/) (2023)
- [A Comprehensive Survey of Challenges and Opportunities of Few-Shot Learning Across Multiple Domains](https://mlsanity.com/paper/2504.04017/) (2025)
- [Meta-Learning for Classifier Selection in Image Datasets: A Feature-Driven Framework for Accuracy Prediction](https://mlsanity.com/paper/2609.11041/) (2026)

## Abstract (arXiv)

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 Challengefootnotehttps://competitions.codalab.org/competitions/26638, demonstrating the advantages of our proposed system. The codes are publicly available at https://github.com/Frozenmad/MetaDelta.