# PRIME: A few primitives can boost robustness to common corruptions

arXiv: https://arxiv.org/abs/2112.13547 · HTML: https://mlsanity.com/paper/2112.13547/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 55 references that are in the map.
- First posted on arXiv 27 Dec 2021.

## Builds on (most cited first, 30 of 39)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (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)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [RobustBench: a standardized adversarial robustness benchmark](https://mlsanity.com/paper/2010.09670/) (2020)
- [Measuring Robustness to Natural Distribution Shifts in Image Classification](https://mlsanity.com/paper/2007.00644/) (2020)
- [Improving robustness against common corruptions by covariate shift adaptation](https://mlsanity.com/paper/2006.16971/) (2020)
- [Information-theoretic analysis of generalization capability of learning algorithms](https://mlsanity.com/paper/1705.07809/) (2017)
- [Understanding Robustness of Transformers for Image Classification](https://mlsanity.com/paper/2103.14586/) (2021)
- [Generalisation in humans and deep neural networks](https://mlsanity.com/paper/1808.08750/) (2018)
- [Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates](https://mlsanity.com/paper/1708.07120/) (2017)
- [Understanding and Mitigating the Tradeoff Between Robustness and Accuracy](https://mlsanity.com/paper/2002.10716/) (2020)
- [Understanding How Image Quality Affects Deep Neural Networks](https://mlsanity.com/paper/1604.04004/) (2016)
- [Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation](https://mlsanity.com/paper/1906.02611/) (2019)
- [On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness](https://mlsanity.com/paper/2102.11273/) (2021)
- [AugMax: Adversarial Composition of Random Augmentations for Robust Training](https://mlsanity.com/paper/2110.13771/) (2021)
- [Analysis of classifiers' robustness to adversarial perturbations](https://mlsanity.com/paper/1502.02590/) (2015)
- [On the effectiveness of adversarial training against common corruptions](https://mlsanity.com/paper/2103.02325/) (2021)
- [Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domain](https://mlsanity.com/paper/2108.08487/) (2021)

## Built on by (most cited first, 30 of 40)

- [A Primer on Bayesian Neural Networks: Review and Debates](https://mlsanity.com/paper/2309.16314/) (2023)
- [A Survey on the Robustness of Computer Vision Models against Common Corruptions](https://mlsanity.com/paper/2305.06024/) (2023)
- [Object-Aware Domain Generalization for Object Detection](https://mlsanity.com/paper/2312.12133/) (2023)
- [Does Robustness on ImageNet Transfer to Downstream Tasks?](https://mlsanity.com/paper/2204.03934/) (2022)
- [Can Biases in ImageNet Models Explain Generalization?](https://mlsanity.com/paper/2404.01509/) (2024)
- [Fourier-basis Functions to Bridge Augmentation Gap: Rethinking Frequency Augmentation in Image Classification](https://mlsanity.com/paper/2403.01944/) (2024)
- [IPMix: Label-Preserving Data Augmentation Method for Training Robust Classifiers](https://mlsanity.com/paper/2310.04780/) (2023)
- [RoDLA: Benchmarking the Robustness of Document Layout Analysis Models](https://mlsanity.com/paper/2403.14442/) (2024)
- [HybridAugment++: Unified Frequency Spectra Perturbations for Model Robustness](https://mlsanity.com/paper/2307.11823/) (2023)
- [Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption Robustness](https://mlsanity.com/paper/2410.03030/) (2024)
- [PhysAug: A Physical-guided and Frequency-based Data Augmentation for Single-Domain Generalized Object Detection](https://mlsanity.com/paper/2412.11807/) (2024)
- [Benchmark Generation Framework with Customizable Distortions for Image Classifier Robustness](https://mlsanity.com/paper/2310.18626/) (2023)
- [RobustCLEVR: A Benchmark and Framework for Evaluating Robustness in Object-centric Learning](https://mlsanity.com/paper/2308.14899/) (2023)
- [Deeper Insights into the Robustness of ViTs towards Common Corruptions](https://mlsanity.com/paper/2204.12143/) (2022)
- [Domain Generalization with Vital Phase Augmentation](https://mlsanity.com/paper/2312.16451/) (2023)
- [Internal Representations of Vision Models Through the Lens of Frames on Data Manifolds](https://mlsanity.com/paper/2211.10558/) (2022)
- [How Do Training Methods Influence the Utilization of Vision Models?](https://mlsanity.com/paper/2410.14470/) (2024)
- [Robust Universal Adversarial Perturbations](https://mlsanity.com/paper/2206.10858/) (2022)
- [Assessing Neural Network Robustness via Adversarial Pivotal Tuning](https://mlsanity.com/paper/2211.09782/) (2022)
- [Singular Value Penalization and Semantic Data Augmentation for Fully Test-Time Adaptation](https://mlsanity.com/paper/2312.08378/) (2023)
- [A Modular System for Enhanced Robustness of Multimedia Understanding Networks via Deep Parametric Estimation](https://mlsanity.com/paper/2402.18402/) (2024)
- [PushPull-Net: Inhibition-driven ResNet robust to image corruptions](https://mlsanity.com/paper/2408.04077/) (2024)
- [DGSSA: Domain generalization with structural and stylistic augmentation for retinal vessel segmentation](https://mlsanity.com/paper/2501.03466/) (2025)
- [Data-Agnostic Augmentations for Unknown Variations: Out-of-Distribution Generalisation in MRI Segmentation](https://mlsanity.com/paper/2505.10223/) (2025)
- [Data augmentation with mixtures of max-entropy transformations for filling-level classification](https://mlsanity.com/paper/2203.04027/) (2022)
- [Robustness and invariance properties of image classifiers](https://mlsanity.com/paper/2209.02408/) (2022)
- [Frequency-Based Vulnerability Analysis of Deep Learning Models against Image Corruptions](https://mlsanity.com/paper/2306.07178/) (2023)
- [A Comprehensive Assessment Benchmark for Rigorously Evaluating Deep Learning Image Classifiers](https://mlsanity.com/paper/2308.04137/) (2023)
- [Label Augmentation for Neural Networks Robustness](https://mlsanity.com/paper/2408.01977/) (2024)
- [One Model, Many Behaviors: Training-Induced Effects on Out-of-Distribution Detection](https://mlsanity.com/paper/2601.10836/) (2026)

## Abstract (arXiv)

Despite their impressive performance on image classification tasks, deep networks have a hard time generalizing to unforeseen corruptions of their data. To fix this vulnerability, prior works have built complex data augmentation strategies, combining multiple methods to enrich the training data. However, introducing intricate design choices or heuristics makes it hard to understand which elements of these methods are indeed crucial for improving robustness. In this work, we take a step back and follow a principled approach to achieve robustness to common corruptions. We propose PRIME, a general data augmentation scheme that relies on simple yet rich families of max-entropy image transformations. PRIME outperforms the prior art in terms of corruption robustness, while its simplicity and plug-and-play nature enable combination with other methods to further boost their robustness. We analyze PRIME to shed light on the importance of the mixing strategy on synthesizing corrupted images, and to reveal the robustness-accuracy trade-offs arising in the context of common corruptions. Finally, we show that the computational efficiency of our method allows it to be easily used in both on-line and off-line data augmentation schemes.