mlsanityData to 14 Oct 2026

Self-Interpretable Model with TransformationEquivariant Interpretation

arXiv 2111.04927 ↗First posted 9 Nov 2021cs.CV cs.LGcited by 21

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a self-interpretable model SITE with transformation-equivariant interpretations. We focus on the robustness and self-consistency of the interpretations of geometric transformations. Apart from the transformation equivariance, as a self-interpretable model, SITE has comparable expressive power as the benchmark black-box classifiers, while being able to present faithful and robust interpretations with high quality. It is worth noticing that although applied in most of the CNN visualization methods, the bilinear upsampling approximation is a rough approximation, which can only provide interpretations in the form of heatmaps (instead of pixel-wise). It remains an open question whether such interpretations can be direct to the input space (as shown in the MNIST experiments). Besides, we consider the translation and rotation transformations in our model. In future work, we will explore the robust interpretations under more complex transformations such as scaling and distortion. Moreover, we clarify that SITE is not limited to geometric transformation (that we used in the computer vision domain), and will explore SITEin other domains in future work.

Key facts. Cited by 21 papers in the map (data through 14 Oct 2026). Builds on 50 of its 85 references that are in the map. First posted on arXiv 9 Nov 2021.

Builds on

50 of 85 references.

References · 50

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  4. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  5. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  6. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  7. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  8. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  9. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  10. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  11. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  12. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
38 more
  1. 2015Spatial Transformer Networkscited by 1,429
  2. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,416
  3. 2018Sanity Checks for Saliency Mapscited by 1,156
  4. 2020Concept Bottleneck Modelscited by 1,032
  5. 2014Striving for Simplicity: The All Convolutional Netcited by 990
  6. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 838
  7. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 746
  8. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 737
  9. 2019Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networkscited by 582
  10. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  11. 2020InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANscited by 394
  12. 2019Is Attention Interpretable?cited by 389
  13. 20183D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Datacited by 354
  14. 2017The (Un)reliability of saliency methodscited by 333
  15. 2016Top-down Neural Attention by Excitation Backpropcited by 321
  16. 2020Neural Additive Models: Interpretable Machine Learning with Neural Netscited by 319
  17. 2019Interpretable machine learning: definitions, methods, and applicationscited by 305
  18. 2016Harmonic Networks: Deep Translation and Rotation Equivariancecited by 295
  19. 2019Understanding Deep Networks via Extremal Perturbations and Smooth Maskscited by 259
  20. 2018Techniques for Interpretable Machine Learningcited by 238
  21. 2019Interpretations are useful: penalizing explanations to align neural networks with prior knowledgecited by 145
  22. 2020Learning to Faithfully Rationalize by Constructioncited by 113
  23. 2017Interpretable Learning for Self-Driving Cars by Visualizing Causal Attentioncited by 107
  24. 2018L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Datacited by 100
  25. 2020On Learning Sets of Symmetric Elementscited by 98
  26. 2019Benchmarking Attribution Methods with Relative Feature Importancecited by 89
  27. 2019Towards Interpretable Reinforcement Learning Using Attention Augmented Agentscited by 82
  28. 2020There and Back Again: Revisiting Backpropagation Saliency Methodscited by 60
  29. 2020Towards Transparent and Explainable Attention Modelscited by 47
  30. 2020Proper Network Interpretability Helps Adversarial Robustness in Classificationcited by 41
  31. 2021Shapley Explanation Networkscited by 41
  32. 2018Human-in-the-Loop Interpretability Priorcited by 36
  33. 2019Equivariant Transformer Networkscited by 35
  34. 2020Deep Transformation-Invariant Clusteringcited by 26
  35. 2020Group Equivariant Deep Reinforcement Learningcited by 24
  36. 2019Learning Generalized Transformation Equivariant Representations via Autoencoding Transformationscited by 22
  37. 2018RotDCF: Decomposition of Convolutional Filters for Rotation-Equivariant Deep Networkscited by 17
  38. 2017Compact Multi-Class Boosted Treescited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 4; 2023: 6; 2024: 5; 2025: 5; 2026: 1.

21 papers.

Sort:

By area:

  1. 2022ProtoVAE: A Trustworthy Self-Explainable Prototypical Variational Modelcited by 34
  2. 2025A Comprehensive Survey on Self-Interpretable Neural Networkscited by 18
  3. 2023Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariancecited by 14
  4. 2025Explain Yourself, Briefly! Self-Explaining Neural Networks with Concise Sufficient Reasonscited by 12
  5. 2022eX-ViT: A Novel eXplainable Vision Transformer for Weakly Supervised Semantic Segmentationcited by 11
  6. 2022A Unified Study of Machine Learning Explanation Evaluation Metricscited by 6
  7. 2023Prototypical Self-Explainable Models Without Re-trainingcited by 6
  8. 2022Bort: Towards Explainable Neural Networks with Bounded Orthogonal Constraintcited by 5
  9. 2024The Gaussian Discriminant Variational Autoencoder (GdVAE): A Self-Explainable Model with Counterfactual Explanationscited by 5
  10. 2025Self-Explaining Neural Networks for Business Process Monitoringcited by 5
  11. 2024Path Choice Matters for Clear Attribution in Path Methodscited by 4
  12. 2023Robustness of Visual Explanations to Common Data Augmentationcited by 3
9 more
  1. 2023Improving Prototypical Visual Explanations with Reward Reweighing, Reselection, and Retrainingcited by 3
  2. 2025Self-Explaining Hypergraph Neural Networks for Diagnosis Predictioncited by 3
  3. 2024Learning the irreversible progression trajectory of Alzheimer's diseasecited by 2
  4. 2024META-ANOVA: Screening interactions for interpretable machine learningcited by 2
  5. 2023A Test Statistic Estimation-based Approach for Establishing Self-interpretable CNN-based Binary Classifierscited by 1
  6. 2023Towards Faithful Neural Network Intrinsic Interpretation with Shapley Additive Self-Attributioncited by 1
  7. 2025Personalized Prediction By Learning Halfspace Reference Classes Under Well-Behaved Distributioncited by 1
  8. 2024Towards White Box Deep Learningcited by 0
  9. 2026Input-Dependent Fisher Information for Local Sensitivity Analysis of Medical Image Classifierscited by 0