mlsanityData to 14 Oct 2026

Non-adversarial Robustness of Deep Learning Methods for Computer Vision

arXiv 2305.14986 ↗First posted 24 May 2023cs.LG cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Non-adversarial robustness, also known as natural robustness, is a property of deep learning models that enables them to maintain performance even when faced with distribution shifts caused by natural variations in data. However, achieving this property is challenging because it is difficult to predict in advance the types of distribution shifts that may occur. To address this challenge, researchers have proposed various approaches, some of which anticipate potential distribution shifts, while others utilize knowledge about the shifts that have already occurred to enhance model generalizability. In this paper, we present a brief overview of the most recent techniques for improving the robustness of computer vision methods, as well as a summary of commonly used robustness benchmark datasets for evaluating the model's performance under data distribution shifts. Finally, we examine the strengths and limitations of the approaches reviewed and identify general trends in deep learning robustness improvement for computer vision.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 51 of its 76 references that are in the map. First posted on arXiv 24 May 2023.

Builds on

51 of 76 references.

References · 51

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  6. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  7. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  8. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  9. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  10. 2016Densely Connected Convolutional Networkscited by 6,720
  11. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  12. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
38 more
  1. 2022Generative Adversarial Networkscited by 5,627
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  4. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  5. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  6. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  7. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  8. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  9. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  10. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
  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
  13. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,515
  14. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  15. 2019Natural Adversarial Examplescited by 1,408
  16. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  17. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,331
  18. 2017Random Erasing Data Augmentationcited by 1,239
  19. 2014How transferable are features in deep neural networks?cited by 1,225
  20. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,152
  21. 2020Meta-Learning in Neural Networks: A Surveycited by 950
  22. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 901
  23. 2022Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distributioncited by 739
  24. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 463
  25. 2020Measuring Robustness to Natural Distribution Shifts in Image Classificationcited by 454
  26. 2018Rethinking ImageNet Pre-trainingcited by 377
  27. 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
  28. 2019A Baseline for Few-Shot Image Classificationcited by 298
  29. 2019Fast AutoAugmentcited by 243
  30. 2018A DIRT-T Approach to Unsupervised Domain Adaptationcited by 215
  31. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 185
  32. 2020Universal Domain Adaptation through Self Supervisioncited by 172
  33. 2019Population Based Augmentation: Efficient Learning of Augmentation Policy Schedulescited by 154
  34. 2019DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Imagescited by 134
  35. 2019Unsupervised Domain Adaptation through Self-Supervisioncited by 116
  36. 2022Image Data Augmentation for Deep Learning: A Surveycited by 96
  37. 2020Online Meta-Learning for Multi-Source and Semi-Supervised Domain Adaptationcited by 64
  38. 2021A Systematic Review of Robustness in Deep Learning for Computer Vision: Mind the gap?cited by 48

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 1; 2026: 1.

6 papers.

  1. 2025Robustness and Cybersecurity in the EU Artificial Intelligence Actcited by 11
  2. 2024Machine Learning Robustness: A Primercited by 8
  3. 2024SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated Corruptions -- An EndoVis'24 Challengecited by 8
  4. 2024Towards Reliable Evaluation of Neural Program Repair with Natural Robustness Testingcited by 5
  5. 2026Robust Ambiguity Detection (RAD) From Model- and Feature-Space Consistencycited by 1
  6. 2023Overview of Deep Learning Methods for Retinal Vessel Segmentationcited by 0