论文标题
通过旋转元学习来增加任务
Task Augmentation by Rotating for Meta-Learning
论文作者
论文摘要
数据增强是提高现代机器学习模型准确性的最有效方法之一，也必须训练深层模型进行元学习。在本文中，我们通过旋转引入了一种任务增强方法，该方法通过旋转原始图像90、180和270度来增加类的数量，这与增加图像数量的传统增强方法不同。通过大量的课程，我们可以在培训期间采样更多样化的任务实例。因此，通过旋转来增加任务增强，使我们能够通过元学习方法训练一个深层网络，几乎不适合。实验结果表明，我们的方法比增加图像数量的旋转要好，并且可以在迷你胶原，CIFAR-FS和FC100少量学习基准测试基准上实现最先进的性能。该代码可在\ url {www.github.com/acechuse/tasklevelaug}上获得。
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}.
