The Effectiveness of Data Augmentation in Image Classification using Deep Learning
The Effectiveness of Data Augmentation in Image Classification using Deep Learning
复制标题
DOI：
--
复制
发表时间：
2017-12
期刊：
影响因子：
--
通讯作者：
Luis Perez;Jason Wang
中科院分区：
文献类型：
--
作者：
Luis Perez;Jason Wang
在本文中，我们探索并将多个解决方案与图像分类中的数据增强问题进行了比较。以前的工作已经通过简单的技术（例如裁剪，旋转和翻转输入图像）证明了数据增强的有效性。我们将对数据的访问限制为ImageNet数据集的一小部分，并依次比较每个数据增强技术。更成功的数据增强策略之一是上面提到的传统转换。我们还试验甘斯以生成不同样式的图像。最后，我们提出了一种允许神经网学习最能改善分类器的增强的方法，我们称之为神经增强。我们在各种数据集上讨论了此方法的成功和缺点。
In this paper, we explore and compare multiple solutions to the problem of data augmentation in image classification. Previous work has demonstrated the effectiveness of data augmentation through simple techniques, such as cropping, rotating, and flipping input images. We artificially constrain our access to data to a small subset of the ImageNet dataset, and compare each data augmentation technique in turn. One of the more successful data augmentations strategies is the traditional transformations mentioned above. We also experiment with GANs to generate images of different styles. Finally, we propose a method to allow a neural net to learn augmentations that best improve the classifier, which we call neural augmentation. We discuss the successes and shortcomings of this method on various datasets.