mlsanityData to 7 Oct 2026

Game-Theoretic Understanding of Misclassification

arXiv 2210.03349 ↗First posted 7 Oct 2022cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

This paper analyzes various types of image misclassification from a game-theoretic view. Particularly, we consider the misclassification of clean, adversarial, and corrupted images and characterize it through the distribution of multi-order interactions. We discover that the distribution of multi-order interactions varies across the types of misclassification. For example, misclassified adversarial images have a higher strength of high-order interactions than correctly classified clean images, which indicates that adversarial perturbations create spurious features that arise from complex cooperation between pixels. By contrast, misclassified corrupted images have a lower strength of low-order interactions than correctly classified clean images, which indicates that corruptions break the local cooperation between pixels. We also provide the first analysis of Vision Transformers using interactions. We found that Vision Transformers show a different tendency in the distribution of interactions from that in CNNs, and this implies that they exploit the features that CNNs do not use for the prediction. Our study demonstrates that the recent game-theoretic analysis of deep learning models can be broadened to analyze various malfunctions of deep learning models including Vision Transformers by using the distribution, order, and sign of interactions.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 21 of its 28 references that are in the map. First posted on arXiv 7 Oct 2022.

Builds on

21 of 28 references.

References · 21

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  6. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  7. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  8. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  9. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  10. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
  11. 2018Robustness May Be at Odds with Accuracycited by 873
  12. 2019A Fourier Perspective on Model Robustness in Computer Visioncited by 288
9 more
  1. 2020A Unified Approach to Interpreting and Boosting Adversarial Transferabilitycited by 71
  2. 2021Discovering and Explaining the Representation Bottleneck of DNNscited by 42
  3. 2021TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothnesscited by 37
  4. 2020Interpreting and Boosting Dropout from a Game-Theoretic Viewcited by 34
  5. 2019Are Adversarial Robustness and Common Perturbation Robustness Independent Attributes ?cited by 25
  6. 2021A Game-Theoretic Taxonomy of Visual Concepts in DNNscited by 16
  7. 2020Addressing Neural Network Robustness with Mixup and Targeted Labeling Adversarial Trainingcited by 10
  8. 2022Exploring Adversarial Robustness of Vision Transformers in the Spectral Perspectivecited by 8
  9. 2022Adversarial amplitude swap towards robust image classifierscited by 1

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Identifying Important Group of Pixels using Interactionscited by 5