mlsanityData to 7 Oct 2026

This Looks Like That: Deep Learning for Interpretable Image Recognition

arXiv 1806.10574 ↗First posted 27 Jun 2018cs.LG cs.AI cs.CVcited by 731

Not on the map. Why?

Abstract (arXiv)

When we are faced with challenging image classification tasks, we often explain our reasoning by dissecting the image, and pointing out prototypical aspects of one class or another. The mounting evidence for each of the classes helps us make our final decision. In this work, we introduce a deep network architecture -- prototypical part network (ProtoPNet), that reasons in a similar way: the network dissects the image by finding prototypical parts, and combines evidence from the prototypes to make a final classification. The model thus reasons in a way that is qualitatively similar to the way ornithologists, physicians, and others would explain to people on how to solve challenging image classification tasks. The network uses only image-level labels for training without any annotations for parts of images. We demonstrate our method on the CUB-200-2011 dataset and the Stanford Cars dataset. Our experiments show that ProtoPNet can achieve comparable accuracy with its analogous non-interpretable counterpart, and when several ProtoPNets are combined into a larger network, it can achieve an accuracy that is on par with some of the best-performing deep models. Moreover, ProtoPNet provides a level of interpretability that is absent in other interpretable deep models.

Key facts. Cited by 731 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 86; 2022: 128; 2023: 134; 2024: 138; 2025: 147; 2026: 98.

731 papers.

Sort:

By area:

  1. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 364
  2. 2022Visual Classification via Description from Large Language Modelscited by 331
  3. 2022Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classificationcited by 310
  4. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 299
  5. 2021Trustworthy AI: From Principles to Practicescited by 206
  6. 2023Localizing Model Behavior with Path Patchingcited by 182
  7. 2022CRAFT: Concept Recursive Activation FacTorization for Explainabilitycited by 177
  8. 2021Explainable artificial intelligence (XAI) in deep learning-based medical image analysiscited by 147
  9. 2022From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagationcited by 141
  10. 2021Benchmarking and Survey of Explanation Methods for Black Box Modelscited by 136
  11. 2022Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networkscited by 126
  12. 2023Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directionscited by 123
38 more
  1. 2021Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypescited by 120
  2. 2021Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyondcited by 116
  3. 2021HIVE: Evaluating the Human Interpretability of Visual Explanationscited by 105
  4. 2023Probabilistic Concept Bottleneck Modelscited by 101
  5. 2021On the Role of Neural Collapse in Transfer Learningcited by 100
  6. 2022AUC Maximization in the Era of Big Data and AI: A Surveycited by 100
  7. 2021Interpretable Image Classification with Differentiable Prototypes Assignmentcited by 97
  8. 2023Concept-based Explainable Artificial Intelligence: A Surveycited by 97
  9. 2021ProtGNN: Towards Self-Explaining Graph Neural Networkscited by 96
  10. 2024Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discoverycited by 91
  11. 2021A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Conceptscited by 90
  12. 2022B-cos Networks: Alignment is All We Need for Interpretabilitycited by 88
  13. 2021The effectiveness of feature attribution methods and its correlation with automatic evaluation scorescited by 87
  14. 2022Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanationscited by 84
  15. 2021Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methodscited by 83
  16. 2021Explainability of deep vision-based autonomous driving systems: Review and challengescited by 80
  17. 2022Concept Bottleneck Model with Additional Unsupervised Conceptscited by 79
  18. 2022Diffusion Models for Counterfactual Explanationscited by 79
  19. 2021Explainable Artificial Intelligence for Autonomous Driving: A Comprehensive Overview and Field Guide for Future Research Directionscited by 73
  20. 2022GlanceNets: Interpretabile, Leak-proof Concept-based Modelscited by 73
  21. 2021XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanationscited by 72
  22. 2021IAIA-BL: A Case-based Interpretable Deep Learning Model for Classification of Mass Lesions in Digital Mammographycited by 72
  23. 2023Discover and Cure: Concept-aware Mitigation of Spurious Correlationcited by 71
  24. 2023A Comprehensive Survey on Applications of Transformers for Deep Learning Taskscited by 70
  25. 2024Morphological Prototyping for Unsupervised Slide Representation Learning in Computational Pathologycited by 70
  26. 2021This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networkscited by 65
  27. 2021Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needscited by 64
  28. 2022Global Explainability of GNNs via Logic Combination of Learned Conceptscited by 64
  29. 2022ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognitioncited by 63
  30. 2022"Help Me Help the AI": Understanding How Explainability Can Support Human-AI Interactioncited by 63
  31. 2023Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcutscited by 63
  32. 2021NICE: An Algorithm for Nearest Instance Counterfactual Explanationscited by 62
  33. 2021Synthetic Benchmarks for Scientific Research in Explainable Machine Learningcited by 59
  34. 2022Visual Recognition with Deep Nearest Centroidscited by 59
  35. 2022Concept Activation Regions: A Generalized Framework For Concept-Based Explanationscited by 57
  36. 2021Convolutional Dynamic Alignment Networks for Interpretable Classificationscited by 54
  37. 2022Rethinking Explainability as a Dialogue: A Practitioner's Perspectivecited by 52
  38. 2022Concept-level Debugging of Part-Prototype Networkscited by 52

50 most cited of 731 All 731 (JSON)