mlsanityData to 7 Oct 2026

Analyzing Effects of Mixed Sample Data Augmentation on Model Interpretability

arXiv 2303.14608 ↗First posted 26 Mar 2023cs.LG cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Mixed sample data augmentation strategies are actively used when training deep neural networks (DNNs). Recent studies suggest that they are effective at various tasks. However, the impact of mixed sample data augmentation on model interpretability has not been widely studied. In this paper, we explore the relationship between model interpretability and mixed sample data augmentation, specifically in terms of feature attribution maps. To this end, we introduce a new metric that allows a comparison of model interpretability while minimizing the impact of occlusion robustness of the model. Experimental results show that several mixed sample data augmentation decreases the interpretability of the model and label mixing during data augmentation plays a significant role in this effect. This new finding suggests it is important to carefully adopt the mixed sample data augmentation method, particularly in applications where attribution map-based interpretability is important.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 56 of its 73 references that are in the map. First posted on arXiv 26 Mar 2023.

Builds on

56 of 73 references.

References · 56

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  7. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  8. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  9. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  10. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  11. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  12. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
38 more
  1. 2020Knowledge Distillation: A Surveycited by 1,578
  2. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  3. 2018Sanity Checks for Saliency Mapscited by 1,149
  4. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  5. 2020Concept Bottleneck Modelscited by 1,022
  6. 2019When Does Label Smoothing Help?cited by 985
  7. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  8. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  9. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 703
  10. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 611
  11. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 604
  12. 2019Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networkscited by 575
  13. 2017Adversarial Patchcited by 514
  14. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 467
  15. 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 416
  16. 2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 304
  17. 2019Understanding Deep Networks via Extremal Perturbations and Smooth Maskscited by 257
  18. 2020Understanding the Role of Individual Units in a Deep Neural Networkcited by 254
  19. 2020Neural Prototype Trees for Interpretable Fine-grained Image Recognitioncited by 213
  20. 2019Full-Gradient Representation for Neural Network Visualizationcited by 189
  21. 2018Tell Me Where to Look: Guided Attention Inference Networkcited by 168
  22. 2020SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularizationcited by 149
  23. 2021PixMix: Dreamlike Pictures Comprehensively Improve Safety Measurescited by 131
  24. 2020Restricting the Flow: Information Bottlenecks for Attributioncited by 110
  25. 2021HIVE: Evaluating the Human Interpretability of Visual Explanationscited by 105
  26. 2022A Consistent and Efficient Evaluation Strategy for Attribution Methodscited by 100
  27. 2019Benchmarking Attribution Methods with Relative Feature Importancecited by 89
  28. 2021The effectiveness of feature attribution methods and its correlation with automatic evaluation scorescited by 87
  29. 2019Multi-scale self-guided attention for medical image segmentationcited by 84
  30. 2021When and How Mixup Improves Calibrationcited by 59
  31. 2021Convolutional Dynamic Alignment Networks for Interpretable Classificationscited by 54
  32. 2022Visual correspondence-based explanations improve AI robustness and human-AI team accuracycited by 37
  33. 2021Neural Response Interpretation through the Lens of Critical Pathwayscited by 32
  34. 2022A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainabilitycited by 30
  35. 2020An Empirical Evaluation on Robustness and Uncertainty of Regularization Methodscited by 28
  36. 2022Towards Better Understanding Attribution Methodscited by 28
  37. 2022TokenMixup: Efficient Attention-guided Token-level Data Augmentation for Transformerscited by 26
  38. 2019MetaMixUp: Learning Adaptive Interpolation Policy of MixUp with Meta-Learningcited by 21

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 0; 2025: 0; 2026: 1.

2 papers.

  1. 2023Robustness of Visual Explanations to Common Data Augmentationcited by 3
  2. 2026S2-FracMix: Label-Preserving Self-Saliency Mixup Augmentationcited by 2