# Data Augmentation for Meta-Learning

arXiv: https://arxiv.org/abs/2010.07092 · HTML: https://mlsanity.com/paper/2010.07092/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Oct 2020.

## Built on by (most cited first, 30 of 38)

- [IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturing](https://mlsanity.com/paper/2301.13359/) (2023)
- [C-Mixup: Improving Generalization in Regression](https://mlsanity.com/paper/2210.05775/) (2022)
- [Meta-Learning with Fewer Tasks through Task Interpolation](https://mlsanity.com/paper/2106.02695/) (2021)
- [Meta Learning for Natural Language Processing: A Survey](https://mlsanity.com/paper/2205.01500/) (2022)
- [Few-Shot Learning with Class Imbalance](https://mlsanity.com/paper/2101.02523/) (2021)
- [What Matters For Meta-Learning Vision Regression Tasks?](https://mlsanity.com/paper/2203.04905/) (2022)
- [Run-Off Election: Improved Provable Defense against Data Poisoning Attacks](https://mlsanity.com/paper/2302.02300/) (2023)
- [On sensitivity of meta-learning to support data](https://mlsanity.com/paper/2110.13953/) (2021)
- [Tree Structure-Aware Few-Shot Image Classification via Hierarchical Aggregation](https://mlsanity.com/paper/2207.06989/) (2022)
- [Robust Fast Adaptation from Adversarially Explicit Task Distribution Generation](https://mlsanity.com/paper/2407.19523/) (2024)
- [Set-based Meta-Interpolation for Few-Task Meta-Learning](https://mlsanity.com/paper/2205.09990/) (2022)
- [MVP: Meta Visual Prompt Tuning for Few-Shot Remote Sensing Image Scene Classification](https://mlsanity.com/paper/2309.09276/) (2023)
- [How to Fine-tune Models with Few Samples: Update, Data Augmentation, and Test-time Augmentation](https://mlsanity.com/paper/2205.07874/) (2022)
- [Robust Meta-learning with Sampling Noise and Label Noise via Eigen-Reptile](https://mlsanity.com/paper/2206.01944/) (2022)
- [Dream to Adapt: Meta Reinforcement Learning by Latent Context Imagination and MDP Imagination](https://mlsanity.com/paper/2311.06673/) (2023)
- [Omni-Training: Bridging Pre-Training and Meta-Training for Few-Shot Learning](https://mlsanity.com/paper/2110.07510/) (2021)
- [Dual-level Mixup for Graph Few-shot Learning with Fewer Tasks](https://mlsanity.com/paper/2502.14158/) (2025)
- [DAC-MR: Data Augmentation Consistency Based Meta-Regularization for Meta-Learning](https://mlsanity.com/paper/2305.07892/) (2023)
- [MetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer Tasks](https://mlsanity.com/paper/2305.10309/) (2023)
- [Task-Distributionally Robust Data-Free Meta-Learning](https://mlsanity.com/paper/2311.14756/) (2023)
- [Semi-Supervised Few-Shot Intent Classification and Slot Filling](https://mlsanity.com/paper/2109.08754/) (2021)
- [Ortho-Shot: Low Displacement Rank Regularization with Data Augmentation for Few-Shot Learning](https://mlsanity.com/paper/2110.09374/) (2021)
- [Few-shot Learning as Cluster-induced Voronoi Diagrams: A Geometric Approach](https://mlsanity.com/paper/2202.02471/) (2022)
- [A Cross-City Federated Transfer Learning Framework: A Case Study on Urban Region Profiling](https://mlsanity.com/paper/2206.00007/) (2022)
- [Few-Shot Learning in Video and 3D Object Detection: A Survey](https://mlsanity.com/paper/2507.17079/) (2025)
- [Towards Better Meta-Initialization with Task Augmentation for Kindergarten-aged Speech Recognition](https://mlsanity.com/paper/2202.12326/) (2022)
- [Interval Bound Interpolation for Few-shot Learning with Few Tasks](https://mlsanity.com/paper/2204.03511/) (2022)
- [Exploiting Style Transfer-based Task Augmentation for Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2301.07927/) (2023)
- [Exploring Active Learning in Meta-Learning: Enhancing Context Set Labeling](https://mlsanity.com/paper/2311.02879/) (2023)
- [RAFIC: Retrieval-Augmented Few-shot Image Classification](https://mlsanity.com/paper/2312.06868/) (2023)

## Abstract (arXiv)

Conventional image classifiers are trained by randomly sampling mini-batches of images. To achieve state-of-the-art performance, practitioners use sophisticated data augmentation schemes to expand the amount of training data available for sampling. In contrast, meta-learning algorithms sample support data, query data, and tasks on each training step. In this complex sampling scenario, data augmentation can be used not only to expand the number of images available per class, but also to generate entirely new classes/tasks. We systematically dissect the meta-learning pipeline and investigate the distinct ways in which data augmentation can be integrated at both the image and class levels. Our proposed meta-specific data augmentation significantly improves the performance of meta-learners on few-shot classification benchmarks.