mlsanityData to 14 Oct 2026

The Co-12 Recipe for Evaluating Interpretable Part-Prototype Image Classifiers

arXiv 2307.14517 ↗First posted 26 Jul 2023cs.CV cs.AIcited by 15

Not on the map. Why?

Abstract (arXiv)

Interpretable part-prototype models are computer vision models that are explainable by design. The models learn prototypical parts and recognise these components in an image, thereby combining classification and explanation. Despite the recent attention for intrinsically interpretable models, there is no comprehensive overview on evaluating the explanation quality of interpretable part-prototype models. Based on the Co-12 properties for explanation quality as introduced in arXiv:2201.08164 (e.g., correctness, completeness, compactness), we review existing work that evaluates part-prototype models, reveal research gaps and outline future approaches for evaluation of the explanation quality of part-prototype models. This paper, therefore, contributes to the progression and maturity of this relatively new research field on interpretable part-prototype models. We additionally provide a ``Co-12 cheat sheet'' that acts as a concise summary of our findings on evaluating part-prototype models.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 39 of its 67 references that are in the map. First posted on arXiv 26 Jul 2023.

Builds on

39 of 67 references.

References · 39

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  2. 2017On Calibration of Modern Neural Networkscited by 4,960
  3. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,552
  4. 2018Sanity Checks for Saliency Mapscited by 1,156
  5. 2018A Survey Of Methods For Explaining Black Box Modelscited by 973
  6. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 737
  7. 2020Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?cited by 599
  8. 2016European Union regulations on algorithmic decision-making and a "right to explanation"cited by 344
  9. 2019Counterfactual Visual Explanationscited by 313
  10. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 302
  11. 2018Metrics for Explainable AI: Challenges and Prospectscited by 260
  12. 2019Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNetcited by 260
27 more
  1. 2019On Completeness-aware Concept-Based Explanations in Deep Neural Networkscited by 239
  2. 2020Neural Prototype Trees for Interpretable Fine-grained Image Recognitioncited by 214
  3. 2020Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?cited by 190
  4. 2019Explaining Classifiers with Causal Concept Effect (CaCE)cited by 135
  5. 2018Net2Vec: Quantifying and Explaining how Concepts are Encoded by Filters in Deep Neural Networkscited by 129
  6. 2021HIVE: Evaluating the Human Interpretability of Visual Explanationscited by 105
  7. 2022A Consistent and Efficient Evaluation Strategy for Attribution Methodscited by 102
  8. 2021What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methodscited by 98
  9. 2021Interpretable Image Classification with Differentiable Prototypes Assignmentcited by 97
  10. 2019Benchmarking Attribution Methods with Relative Feature Importancecited by 89
  11. 2020ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discoverycited by 89
  12. 2021The effectiveness of feature attribution methods and its correlation with automatic evaluation scorescited by 88
  13. 2021The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanationscited by 87
  14. 2021This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networkscited by 65
  15. 2021Understanding Softmax Confidence and Uncertaintycited by 63
  16. 2022ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognitioncited by 63
  17. 2021Randomness In Neural Network Training: Characterizing The Impact of Toolingcited by 59
  18. 2021Synthetic Benchmarks for Scientific Research in Explainable Machine Learningcited by 59
  19. 2020This Looks Like That, Because ... Explaining Prototypes for Interpretable Image Recognitioncited by 50
  20. 2021Nondeterminism and Instability in Neural Network Optimizationcited by 48
  21. 2021The Who in XAI: How AI Background Shapes Perceptions of AI Explanationscited by 48
  22. 2021This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagationcited by 43
  23. 2022ViT-CX: Causal Explanation of Vision Transformerscited by 28
  24. 2022Knowledge Distillation to Ensemble Global and Interpretable Prototype-Based Mammogram Classification Modelscited by 11
  25. 2020Towards Robust Fine-grained Recognition by Maximal Separation of Discriminative Featurescited by 5
  26. 2022Towards Human-Interpretable Prototypes for Visual Assessment of Image Classification Modelscited by 4
  27. 2023Sanity checks and improvements for patch visualisation in prototype-based image classificationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 8; 2025: 5; 2026: 2.

15 papers.

Sort:

By area:

  1. 2024Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspectivecited by 9
  2. 2024PIPNet3D: Interpretable Detection of Alzheimer in MRI Scanscited by 3
  3. 2024Prototype-based Interpretable Breast Cancer Prediction Models: Analysis and Challengescited by 3
  4. 2025This looks like what? Challenges and Future Research Directions for Part-Prototype Modelscited by 3
  5. 2024XEQ Scale for Evaluating XAI Experience Qualitycited by 2
  6. 2024Patch-based Intuitive Multimodal Prototypes Network (PIMPNet) for Alzheimer's Disease classificationcited by 2
  7. 2024Revisiting FunnyBirds evaluation framework for prototypical parts networkscited by 2
  8. 2025A Survey on Interpretability in Visual Recognitioncited by 2
  9. 2025From Confusion to Clarity: ProtoScore -- A Framework for Evaluating Prototype-Based XAIcited by 2
  10. 2026The Case for Model Science: Verify, Explore, Steer, Refinecited by 2
  11. 2025Comprehensive Evaluation of Prototype Neural Networkscited by 1
  12. 2024NormEnsembleXAI: Unveiling the Strengths and Weaknesses of XAI Ensemble Techniquescited by 0
3 more
  1. 2024Beyond the Veil of Similarity: Quantifying Semantic Continuity in Explainable AIcited by 0
  2. 2025ProtoMask: Segmentation-Guided Prototype Learningcited by 0
  3. 2026Verifying the Linear Representation Hypothesis: How Interpretable Are Vision SAEs?cited by 0