Albumentations: Fast and Flexible Image Augmentations
Albumentations: Fast and Flexible Image Augmentations
复制标题
DOI：
10.3390/info11020125
复制
发表时间：
2020-02-01
期刊：
影响因子：
3.1
通讯作者：
Kalinin, Alexandr A.
中科院分区：
文献类型：
--
作者：
Buslaev, Alexander;Iglovikov, Vladimir I.;Kalinin, Alexandr A.
数据增强是一种常用的技术，通过利用保留相应输出标签的输入转换来增加标记训练集的大小和多样性。在计算机视觉中，图像增强已成为一种常见的隐式正则化技术，用于对抗深度学习模型中的过度拟合，并普遍用于提高性能。虽然大多数深度学习框架都实现基本的图像转换，但该列表通常仅限于翻转、旋转、缩放和裁剪的某些变化。此外，现有图像增强库中的图像处理速度各不相同。我们推出了 Albumentations，这是一个快速、灵活的开源库，用于图像增强，具有多种可用的图像变换操作，它也是其他增强库的易于使用的包装器。我们讨论了推动专辑实施的设计原则，并概述了关键特性和独特功能。最后，我们提供了针对不同计算机视觉任务的图像增强示例，并证明在大多数图像转换操作上，Albumentations 比其他常用的图像增强工具更快。
Data augmentation is a commonly used technique for increasing both the size and the diversity of labeled training sets by leveraging input transformations that preserve corresponding output labels. In computer vision, image augmentations have become a common implicit regularization technique to combat overfitting in deep learning models and are ubiquitously used to improve performance. While most deep learning frameworks implement basic image transformations, the list is typically limited to some variations of flipping, rotating, scaling, and cropping. Moreover, image processing speed varies in existing image augmentation libraries. We present Albumentations, a fast and flexible open source library for image augmentation with many various image transform operations available that is also an easy-to-use wrapper around other augmentation libraries. We discuss the design principles that drove the implementation of Albumentations and give an overview of the key features and distinct capabilities. Finally, we provide examples of image augmentations for different computer vision tasks and demonstrate that Albumentations is faster than other commonly used image augmentation tools on most image transform operations.