arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2201.06494cs.AIcs.CV
收藏

AugLy:稳健性的数据增强

AugLy: Data Augmentations for Robustness

Meta AI

Zoe Papakipos, Joanna Bitton

摘要:

我们介绍AugLy,一个专注于对抗鲁棒性的数据增强库。AugLy为多种模态(音频,图像,文本和视频)提供了广泛的增强。这些增强的灵感来自于真实用户在社交媒体平台上执行的操作,其中一些还没有得到现有数据增强库的支持。AugLy可以用于任何需要数据增强的目的,但它特别适合评估鲁棒性和系统地生成对抗攻击。在本文中,我们介绍了AugLy的工作原理,将其与现有库进行基准比较,并使用它来评估各种最先进模型的鲁棒性,以展示AugLy的实用性。AugLy存储库可以在https://github.com/facebookresearch/AugLy上找到。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑