# AugLy: Data Augmentations for Robustness

arXiv: https://arxiv.org/abs/2201.06494 · HTML: https://mlsanity.com/paper/2201.06494/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 29 references that are in the map.
- First posted on arXiv 17 Jan 2022.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [A Survey of Data Augmentation Approaches for NLP](https://mlsanity.com/paper/2105.03075/) (2021)
- [Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation](https://mlsanity.com/paper/1911.03842/) (2019)
- [TorchAudio: Building Blocks for Audio and Speech Processing](https://mlsanity.com/paper/2110.15018/) (2021)
- [Data Augmenting Contrastive Learning of Speech Representations in the Time Domain](https://mlsanity.com/paper/2007.00991/) (2020)
- [VideoMix: Rethinking Data Augmentation for Video Classification](https://mlsanity.com/paper/2012.03457/) (2020)
- [PyTorchVideo: A Deep Learning Library for Video Understanding](https://mlsanity.com/paper/2111.09887/) (2021)
- [Hi, my name is Martha: Using names to measure and mitigate bias in generative dialogue models](https://mlsanity.com/paper/2109.03300/) (2021)

## Built on by (most cited first, 30 of 34)

- [Visual Programming: Compositional visual reasoning without training](https://mlsanity.com/paper/2211.11559/) (2022)
- [The Stable Signature: Rooting Watermarks in Latent Diffusion Models](https://mlsanity.com/paper/2303.15435/) (2023)
- ["I'm sorry to hear that": Finding New Biases in Language Models with a Holistic Descriptor Dataset](https://mlsanity.com/paper/2205.09209/) (2022)
- [AugGPT: Leveraging ChatGPT for Text Data Augmentation](https://mlsanity.com/paper/2302.13007/) (2023)
- [A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others](https://mlsanity.com/paper/2212.04825/) (2022)
- [Perturbation Augmentation for Fairer NLP](https://mlsanity.com/paper/2205.12586/) (2022)
- [Toxicity in Multilingual Machine Translation at Scale](https://mlsanity.com/paper/2210.03070/) (2022)
- [Multilingual Holistic Bias: Extending Descriptors and Patterns to Unveil Demographic Biases in Languages at Scale](https://mlsanity.com/paper/2305.13198/) (2023)
- [Out-Of-Distribution Detection Is Not All You Need](https://mlsanity.com/paper/2211.16158/) (2022)
- [Audio-Visual Contrastive Learning with Temporal Self-Supervision](https://mlsanity.com/paper/2302.07702/) (2023)
- [Evaluating Out-of-Distribution Performance on Document Image Classifiers](https://mlsanity.com/paper/2210.07448/) (2022)
- [Augraphy: A Data Augmentation Library for Document Images](https://mlsanity.com/paper/2208.14558/) (2022)
- [RoDLA: Benchmarking the Robustness of Document Layout Analysis Models](https://mlsanity.com/paper/2403.14442/) (2024)
- [Hybrid Multimodal Feature Extraction, Mining and Fusion for Sentiment Analysis](https://mlsanity.com/paper/2208.03051/) (2022)
- [Results and findings of the 2021 Image Similarity Challenge](https://mlsanity.com/paper/2202.04007/) (2022)
- [The 2023 Video Similarity Dataset and Challenge](https://mlsanity.com/paper/2306.09489/) (2023)
- [FairDistillation: Mitigating Stereotyping in Language Models](https://mlsanity.com/paper/2207.04546/) (2022)
- [Active Image Indexing](https://mlsanity.com/paper/2210.10620/) (2022)
- [HateProof: Are Hateful Meme Detection Systems really Robust?](https://mlsanity.com/paper/2302.05703/) (2023)
- [VADER: Video Alignment Differencing and Retrieval](https://mlsanity.com/paper/2303.13193/) (2023)
- [Adversarial Text Normalization](https://mlsanity.com/paper/2206.04137/) (2022)
- [A Survey on Uncertainty Toolkits for Deep Learning](https://mlsanity.com/paper/2205.01040/) (2022)
- [An Exploratory Study of AI System Risk Assessment from the Lens of Data Distribution and Uncertainty](https://mlsanity.com/paper/2212.06828/) (2022)
- [Enhancing object detection robustness: A synthetic and natural perturbation approach](https://mlsanity.com/paper/2304.10622/) (2023)
- [URET: Universal Robustness Evaluation Toolkit (for Evasion)](https://mlsanity.com/paper/2308.01840/) (2023)
- [SOTASTREAM: A Streaming Approach to Machine Translation Training](https://mlsanity.com/paper/2308.07489/) (2023)
- [Joint Engagement Classification using Video Augmentation Techniques for Multi-person Human-robot Interaction](https://mlsanity.com/paper/2212.14128/) (2022)
- [Data Augmentation for Neural NLP](https://mlsanity.com/paper/2302.11412/) (2023)
- [Can we Defend Against the Unknown? An Empirical Study About Threshold Selection for Neural Network Monitoring](https://mlsanity.com/paper/2405.08654/) (2024)
- [LookupForensics: A Large-Scale Multi-Task Dataset for Multi-Phase Image-Based Fact Verification](https://mlsanity.com/paper/2407.18614/) (2024)

## Abstract (arXiv)

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.