# Task Augmentation by Rotating for Meta-Learning

arXiv: https://arxiv.org/abs/2003.00804 · HTML: https://mlsanity.com/paper/2003.00804/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Feb 2020.

## Built on by (most cited first, 18 of 18)

- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [Neuralizer: General Neuroimage Analysis without Re-Training](https://mlsanity.com/paper/2305.02644/) (2023)
- [EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients](https://mlsanity.com/paper/2201.09699/) (2022)
- [The Effect of Diversity in Meta-Learning](https://mlsanity.com/paper/2201.11775/) (2022)
- [Multimodality in Meta-Learning: A Comprehensive Survey](https://mlsanity.com/paper/2109.13576/) (2021)
- [ProtoTransformer: A Meta-Learning Approach to Providing Student Feedback](https://mlsanity.com/paper/2107.14035/) (2021)
- [DAC-MR: Data Augmentation Consistency Based Meta-Regularization for Meta-Learning](https://mlsanity.com/paper/2305.07892/) (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)
- [Enhancing Prototypical Few-Shot Learning by Leveraging the Local-Level Strategy](https://mlsanity.com/paper/2111.04331/) (2021)
- [A Statistical Model for Predicting Generalization in Few-Shot Classification](https://mlsanity.com/paper/2212.06461/) (2022)
- [Towards Better Meta-Initialization with Task Augmentation for Kindergarten-aged Speech Recognition](https://mlsanity.com/paper/2202.12326/) (2022)
- [Multilevel Saliency-Guided Self-Supervised Learning for Image Anomaly Detection](https://mlsanity.com/paper/2311.18332/) (2023)
- [Learning to generate imaginary tasks for improving generalization in meta-learning](https://mlsanity.com/paper/2206.04335/) (2022)
- [Disambiguation of One-Shot Visual Classification Tasks: A Simplex-Based Approach](https://mlsanity.com/paper/2301.06372/) (2023)
- [Improving Generalization in Meta-Learning via Meta-Gradient Augmentation](https://mlsanity.com/paper/2306.08460/) (2023)
- [ViT-ProtoNet for Few-Shot Image Classification: A Multi-Benchmark Evaluation](https://mlsanity.com/paper/2507.09299/) (2025)

## Abstract (arXiv)

Data augmentation is one of the most effective approaches for improving the accuracy of modern machine learning models, and it is also indispensable to train a deep model for meta-learning. In this paper, we introduce a task augmentation method by rotating, which increases the number of classes by rotating the original images 90, 180 and 270 degrees, different from traditional augmentation methods which increase the number of images. With a larger amount of classes, we can sample more diverse task instances during training. Therefore, task augmentation by rotating allows us to train a deep network by meta-learning methods with little over-fitting. Experimental results show that our approach is better than the rotation for increasing the number of images and achieves state-of-the-art performance on miniImageNet, CIFAR-FS, and FC100 few-shot learning benchmarks. The code is available on urlwww.github.com/AceChuse/TaskLevelAug.