Task Augmentation by Rotating for Meta-Learning

Abstract

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 \url{www.github.com/AceChuse/TaskLevelAug}.

9 pages

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Improving neural networks by preventing co-adaptation of feature detectors
• Prototypical Networks for Few-shot Learning
• A Simple Neural Attentive Meta-Learner
• Data Augmentation Generative Adversarial Networks
• DropBlock: A regularization method for convolutional networks
• Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments
• Learning to Support: Exploiting Structure Information in Support Sets for One-Shot Learning

Cited by in corpus (5)

• Meta-Learning Requires Meta-Augmentation
• Data Augmentation for Meta-Learning
• ProtoTransformer: A Meta-Learning Approach to Providing Student Feedback
• Is Support Set Diversity Necessary for Meta-Learning?
• Semi-Supervised Few-Shot Intent Classification and Slot Filling