mlsanityData to 7 Oct 2026

AugLy: Data Augmentations for Robustness

arXiv 2201.06494 ↗First posted 17 Jan 2022cs.AI cs.CVcited by 34

Not on the map. Why?

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.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Builds on 16 of its 29 references that are in the map. First posted on arXiv 17 Jan 2022.

Builds on

16 of 29 references.

References · 16

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  4. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  5. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,842
  6. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
  7. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  8. 2018Gender Bias in Coreference Resolution: Evaluation and Debiasing Methodscited by 657
  9. 2018Albumentations: fast and flexible image augmentationscited by 558
  10. 2021A Survey of Data Augmentation Approaches for NLPcited by 408
  11. 2019Queens are Powerful too: Mitigating Gender Bias in Dialogue Generationcited by 152
  12. 2021TorchAudio: Building Blocks for Audio and Speech Processingcited by 83
4 more
  1. 2020Data Augmenting Contrastive Learning of Speech Representations in the Time Domaincited by 63
  2. 2020VideoMix: Rethinking Data Augmentation for Video Classificationcited by 55
  3. 2021PyTorchVideo: A Deep Learning Library for Video Understandingcited by 32
  4. 2021Hi, my name is Martha: Using names to measure and mitigate bias in generative dialogue modelscited by 23

Built on by

Cited by year

Citing papers per year: 2022: 16; 2023: 12; 2024: 5; 2025: 1.

34 papers.

Sort:

By area:

  1. 2022Visual Programming: Compositional visual reasoning without trainingcited by 507
  2. 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Modelscited by 289
  3. 2022"I'm sorry to hear that": Finding New Biases in Language Models with a Holistic Descriptor Datasetcited by 160
  4. 2023AugGPT: Leveraging ChatGPT for Text Data Augmentationcited by 128
  5. 2022A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Otherscited by 85
  6. 2022Perturbation Augmentation for Fairer NLPcited by 51
  7. 2022Toxicity in Multilingual Machine Translation at Scalecited by 26
  8. 2022Out-Of-Distribution Detection Is Not All You Needcited by 23
  9. 2023Multilingual Holistic Bias: Extending Descriptors and Patterns to Unveil Demographic Biases in Languages at Scalecited by 23
  10. 2023Audio-Visual Contrastive Learning with Temporal Self-Supervisioncited by 18
  11. 2022Evaluating Out-of-Distribution Performance on Document Image Classifierscited by 16
  12. 2022Augraphy: A Data Augmentation Library for Document Imagescited by 14
22 more
  1. 2022Hybrid Multimodal Feature Extraction, Mining and Fusion for Sentiment Analysiscited by 12
  2. 2024RoDLA: Benchmarking the Robustness of Document Layout Analysis Modelscited by 12
  3. 2022Results and findings of the 2021 Image Similarity Challengecited by 10
  4. 2023The 2023 Video Similarity Dataset and Challengecited by 9
  5. 2022FairDistillation: Mitigating Stereotyping in Language Modelscited by 8
  6. 2022Active Image Indexingcited by 8
  7. 2023HateProof: Are Hateful Meme Detection Systems really Robust?cited by 7
  8. 2023VADER: Video Alignment Differencing and Retrievalcited by 6
  9. 2022Adversarial Text Normalizationcited by 5
  10. 2022A Survey on Uncertainty Toolkits for Deep Learningcited by 4
  11. 2022An Exploratory Study of AI System Risk Assessment from the Lens of Data Distribution and Uncertaintycited by 3
  12. 2023Enhancing object detection robustness: A synthetic and natural perturbation approachcited by 3
  13. 2023URET: Universal Robustness Evaluation Toolkit (for Evasion)cited by 3
  14. 2023SOTASTREAM: A Streaming Approach to Machine Translation Trainingcited by 3
  15. 2022Joint Engagement Classification using Video Augmentation Techniques for Multi-person Human-robot Interactioncited by 2
  16. 2023Data Augmentation for Neural NLPcited by 2
  17. 2024Can we Defend Against the Unknown? An Empirical Study About Threshold Selection for Neural Network Monitoringcited by 2
  18. 2024LookupForensics: A Large-Scale Multi-Task Dataset for Multi-Phase Image-Based Fact Verificationcited by 2
  19. 2024Clarifying Myths About the Relationship Between Shape Bias, Accuracy, and Robustnesscited by 1
  20. 2025Language Models as Semantic Teachers: Post-Training Alignment for Medical Audio Understandingcited by 1
  21. 2023Boosting Generalization with Adaptive Style Techniques for Fingerprint Liveness Detectioncited by 0
  22. 2024Towards Massive Multilingual Holistic Biascited by 0