论文标题
Augly：鲁棒性数据增强
AugLy: Data Augmentations for Robustness
论文作者
论文摘要
我们介绍了Augly，这是一个数据增强库，侧重于对抗性鲁棒性。 Augly为多种模式（音频，图像，文本和视频）提供了广泛的增强。这些扩展的灵感来自真实用户在社交媒体平台上执行的功能，其中一些尚未得到现有数据增强库的支持。 Augly可用于任何有用数据有用的目的，但特别适合评估鲁棒性和系统地产生对抗性攻击。在本文中，我们介绍了Augly的工作原理，将其与现有库进行比较，并使用它来评估各种最先进模型的稳健性，以展示Augly的实用程序。可以在https://github.com/facebookresearch/augly上找到Augly存储库。
We introduce AugLy, a data augmentation library with a focus on adversarial robustness. AugLy provides a wide array of augmentations for multiple modalities (audio, image, text, & video). These augmentations were inspired by those that real users perform on social media platforms, some of which were not already supported by existing data augmentation libraries. AugLy can be used for any purpose where data augmentations are useful, but it is particularly well-suited for evaluating robustness and systematically generating adversarial attacks. In this paper we present how AugLy works, benchmark it compared against existing libraries, and use it to evaluate the robustness of various state-of-the-art models to showcase AugLy's utility. The AugLy repository can be found at https://github.com/facebookresearch/AugLy.
