mlsanityData to 14 Oct 2026

PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures

arXiv 2112.05135 ↗First posted 9 Dec 2021cs.LG cs.CVcited by 131

Not on the map. Why?

Abstract (arXiv)

In real-world applications of machine learning, reliable and safe systems must consider measures of performance beyond standard test set accuracy. These other goals include out-of-distribution (OOD) robustness, prediction consistency, resilience to adversaries, calibrated uncertainty estimates, and the ability to detect anomalous inputs. However, improving performance towards these goals is often a balancing act that today's methods cannot achieve without sacrificing performance on other safety axes. For instance, adversarial training improves adversarial robustness but sharply degrades other classifier performance metrics. Similarly, strong data augmentation and regularization techniques often improve OOD robustness but harm anomaly detection, raising the question of whether a Pareto improvement on all existing safety measures is possible. To meet this challenge, we design a new data augmentation strategy utilizing the natural structural complexity of pictures such as fractals, which outperforms numerous baselines, is near Pareto-optimal, and roundly improves safety measures.

Key facts. Cited by 131 papers in the map (data through 14 Oct 2026). Builds on 42 of its 58 references that are in the map. First posted on arXiv 9 Dec 2021.

Builds on

42 of 58 references.

References · 42

  1. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  3. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  4. 2017On Calibration of Modern Neural Networkscited by 4,960
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  6. 2016Wide Residual Networkscited by 3,070
  7. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  8. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  9. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  10. 2013Describing Textures in the Wildcited by 2,125
  11. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,850
  12. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
30 more
  1. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  2. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
  3. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
  4. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  5. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  6. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,287
  7. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,247
  8. 2017Random Erasing Data Augmentationcited by 1,239
  9. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  10. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 901
  11. 2018Robustness May Be at Odds with Accuracycited by 880
  12. 2018AutoAugment: Learning Augmentation Policies from Datacited by 730
  13. 2021How to train your ViT? Data, Augmentation, and Regularization in Vision Transformerscited by 569
  14. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 514
  15. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 425
  16. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  17. 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
  18. 2021Unsolved Problems in ML Safetycited by 292
  19. 2019A Fourier Perspective on Model Robustness in Computer Visioncited by 288
  20. 2018Learning Confidence for Out-of-Distribution Detection in Neural Networkscited by 245
  21. 2019Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentationcited by 105
  22. 2021Pre-training without Natural Imagescited by 100
  23. 2021On Interaction Between Augmentations and Corruptions in Natural Corruption Robustnesscited by 97
  24. 2021Learning to See by Looking at Noisecited by 92
  25. 2018Data Augmentation using Random Image Cropping and Patching for Deep CNNscited by 88
  26. 2015Posterior calibration and exploratory analysis for natural language processing modelscited by 76
  27. 2017Between-class Learning for Image Classificationcited by 50
  28. 2021Can Vision Transformers Learn without Natural Images?cited by 32
  29. 2020An Empirical Evaluation on Robustness and Uncertainty of Regularization Methodscited by 28
  30. 2021VisDA-2021 Competition Universal Domain Adaptation to Improve Performance on Out-of-Distribution Datacited by 19

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 22; 2023: 37; 2024: 33; 2025: 23; 2026: 16.

131 papers.

Sort:

By area:

  1. 2025Humanity's Last Examcited by 491
  2. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 268
  3. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 179
  4. 2023Leaving Reality to Imagination: Robust Classification via Generated Datasetscited by 91
  5. 2023FLIRT: Feedback Loop In-context Red Teamingcited by 83
  6. 2024DiffuseMix: Label-Preserving Data Augmentation with Diffusion Modelscited by 78
  7. 2022SVFormer: Semi-supervised Video Transformer for Action Recognitioncited by 68
  8. 2023On Pitfalls of Test-Time Adaptationcited by 64
  9. 2024Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?cited by 61
  10. 2022Eliciting and Learning with Soft Labels from Every Annotatorcited by 43
  11. 2024Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectivescited by 37
  12. 2022A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainabilitycited by 31
38 more
  1. 2022Large-scale Robustness Analysis of Video Action Recognition Modelscited by 29
  2. 2022On the Strong Correlation Between Model Invariance and Generalizationcited by 23
  3. 2022You Only Cut Once: Boosting Data Augmentation with a Single Cutcited by 22
  4. 2023A Survey on the Robustness of Computer Vision Models against Common Corruptionscited by 21
  5. 2023A Closer Look at Model Adaptation using Feature Distortion and Simplicity Biascited by 20
  6. 2023Strong but simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learningcited by 20
  7. 2024Can Biases in ImageNet Models Explain Generalization?cited by 20
  8. 2024Intelligent Clinical Documentation: Harnessing Generative AI for Patient-Centric Clinical Note Generationcited by 20
  9. 2024A Survey on Mixup Augmentations and Beyondcited by 20
  10. 2022Not Just Pretty Pictures: Toward Interventional Data Augmentation Using Text-to-Image Generatorscited by 17
  11. 2022Concept-based Explanations for Out-Of-Distribution Detectorscited by 16
  12. 2024AdaNeg: Adaptive Negative Proxy Guided OOD Detection with Vision-Language Modelscited by 16
  13. 2023How Reliable is Your Regression Model's Uncertainty Under Real-World Distribution Shifts?cited by 14
  14. 2023IPMix: Label-Preserving Data Augmentation Method for Training Robust Classifierscited by 14
  15. 2024GenMix: Effective Data Augmentation with Generative Diffusion Model Image Editingcited by 14
  16. 2025Handling Out-of-Distribution Data: A Surveycited by 14
  17. 2023OOD-CV-v2: An extended Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Imagescited by 12
  18. 2023HybridAugment++: Unified Frequency Spectra Perturbations for Model Robustnesscited by 12
  19. 2024SUMix: Mixup with Semantic and Uncertain Informationcited by 12
  20. 2024ReMoDetect: Reward Models Recognize Aligned LLM's Generationscited by 11
  21. 2022When Neural Networks Fail to Generalize? A Model Sensitivity Perspectivecited by 10
  22. 2022Aries: Efficient Testing of Deep Neural Networks via Labeling-Free Accuracy Estimationcited by 9
  23. 2023R-Mixup: Riemannian Mixup for Biological Networkscited by 9
  24. 2024Energy-based Hopfield Boosting for Out-of-Distribution Detectioncited by 9
  25. 2025Context-guided Responsible Data Augmentation with Diffusion Modelscited by 9
  26. 2022CropMix: Sampling a Rich Input Distribution via Multi-Scale Croppingcited by 8
  27. 2022Human-in-the-Loop Mixupcited by 8
  28. 2023Calibrated Out-of-Distribution Detection with a Generic Representationcited by 8
  29. 2023Learning Better with Less: Effective Augmentation for Sample-Efficient Visual Reinforcement Learningcited by 8
  30. 2023A Re-Parameterized Vision Transformer (ReVT) for Domain-Generalized Semantic Segmentationcited by 8
  31. 2023Generalization Analogies: A Testbed for Generalizing AI Oversight to Hard-To-Measure Domainscited by 8
  32. 2024Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networkscited by 8
  33. 2024A Unified Approach Towards Active Learning and Out-of-Distribution Detectioncited by 7
  34. 2025AdaSCALE: Adaptive Scaling for OOD Detectioncited by 7
  35. 2024Out-of-Distribution Data: An Acquaintance of Adversarial Examples -- A Surveycited by 6
  36. 2025Graph Synthetic Out-of-Distribution Exposure with Large Language Modelscited by 6
  37. 2022Deeper Insights into the Robustness of ViTs towards Common Corruptionscited by 5
  38. 2022Diffusion Denoising Process for Perceptron Bias in Out-of-distribution Detectioncited by 5

50 most cited of 131 All 131 (JSON)