mlsanityData to 7 Oct 2026

This looks like what? Challenges and Future Research Directions for Part-Prototype Models

arXiv 2502.09340 ↗First posted 13 Feb 2025cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

The growing interest in eXplainable Artificial Intelligence (XAI) has stimulated research on models with built-in interpretability, among which part-prototype models are particularly prominent. Part-Prototype Models (PPMs) classify inputs by comparing them to learned prototypes and provide human-understandable explanations of the form "this looks like that". Despite this intrinsic interpretability, PPMs have not yet emerged as a competitive alternative to post-hoc explanation methods. This survey reviews work published between 2019 and 2025 and derives a taxonomy of the challenges faced by current PPMs. The analysis reveals a diverse set of open problems. The main issue concerns the quality and number of learned prototypes. Further challenges include limited generalization across tasks and contexts, as well as methodological shortcomings such as non-standardized evaluation. Five broad research directions are identified: improving predictive performance, developing theoretically grounded architectures, establishing frameworks for human-AI collaboration, aligning models with human concepts, and defining robust metrics and benchmarks for evaluation. The survey aims to stimulate further research and promote intrinsically interpretable models for practical applications. A curated list of the surveyed papers is available at https://github.com/aix-group/ppm-survey.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 48 of its 69 references that are in the map. First posted on arXiv 13 Feb 2025.

Builds on

48 of 69 references.

References · 48

  1. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  2. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  3. 2020Concept Bottleneck Modelscited by 1,022
  4. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  5. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 299
  6. 2020Neural Prototype Trees for Interpretable Fine-grained Image Recognitioncited by 213
  7. 2021Trustworthy AI: From Principles to Practicescited by 206
  8. 2021Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypescited by 120
  9. 2021HIVE: Evaluating the Human Interpretability of Visual Explanationscited by 105
  10. 2021Interpretable Image Classification with Differentiable Prototypes Assignmentcited by 97
  11. 2021ProtGNN: Towards Self-Explaining Graph Neural Networkscited by 96
  12. 2020ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discoverycited by 89
36 more
  1. 2024Is Cosine-Similarity of Embeddings Really About Similarity?cited by 89
  2. 2021XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanationscited by 72
  3. 2021IAIA-BL: A Case-based Interpretable Deep Learning Model for Classification of Mass Lesions in Digital Mammographycited by 72
  4. 2024Morphological Prototyping for Unsupervised Slide Representation Learning in Computational Pathologycited by 70
  5. 2022ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognitioncited by 63
  6. 2022Concept-level Debugging of Part-Prototype Networkscited by 52
  7. 2020This Looks Like That, Because ... Explaining Prototypes for Interpretable Image Recognitioncited by 50
  8. 2023FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methodscited by 49
  9. 2021This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagationcited by 43
  10. 2021Independent Prototype Propagation for Zero-Shot Compositionalitycited by 42
  11. 2023Learning Support and Trivial Prototypes for Interpretable Image Classificationcited by 38
  12. 2022Evaluation and Improvement of Interpretability for Self-Explainable Part-Prototype Networkscited by 37
  13. 2023This Looks Like Those: Illuminating Prototypical Concepts Using Multiple Visualizationscited by 36
  14. 2022Explainable Deep Learning Methods in Medical Image Classification: A Surveycited by 31
  15. 2023Interpretability Benchmark for Evaluating Spatial Misalignment of Prototypical Parts Explanationscited by 27
  16. 2024Interpretable Image Classification with Adaptive Prototype-based Vision Transformerscited by 25
  17. 2023ICICLE: Interpretable Class Incremental Continual Learningcited by 24
  18. 2022Proto2Proto: Can you recognize the car, the way I do?cited by 23
  19. 2021ProtoMIL: Multiple Instance Learning with Prototypical Parts for Whole-Slide Image Classificationcited by 22
  20. 2024Prototypical Hash Encoding for On-the-Fly Fine-Grained Category Discoverycited by 19
  21. 2023Pixel-Grounded Prototypical Part Networkscited by 18
  22. 2023The Co-12 Recipe for Evaluating Interpretable Part-Prototype Image Classifierscited by 15
  23. 2024LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Visioncited by 15
  24. 2022Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methodscited by 13
  25. 2023Interpreting and Correcting Medical Image Classification with PIP-Netcited by 11
  26. 2023On the Interpretability of Part-Prototype Based Classifiers: A Human Centric Analysiscited by 11
  27. 2023Keep the Faith: Faithful Explanations in Convolutional Neural Networks for Case-Based Reasoningcited by 10
  28. 2024MCPNet: An Interpretable Classifier via Multi-Level Concept Prototypescited by 10
  29. 2023Sanity checks for patch visualisation in prototype-based image classificationcited by 8
  30. 2022A Lightweight, Efficient and Explainable-by-Design Convolutional Neural Network for Internet Traffic Classificationcited by 6
  31. 2022Learning to Select Prototypical Parts for Interpretable Sequential Data Modelingcited by 4
  32. 2023Improving Prototypical Visual Explanations with Reward Reweighing, Reselection, and Retrainingcited by 3
  33. 2024Prototype-based Interpretable Breast Cancer Prediction Models: Analysis and Challengescited by 3
  34. 2024This Probably Looks Exactly Like That: An Invertible Prototypical Networkcited by 3
  35. 2023PROMINET: Prototype-based Multi-View Network for Interpretable Email Response Predictioncited by 2
  36. 2024Patch-based Intuitive Multimodal Prototypes Network (PIMPNet) for Alzheimer's Disease classificationcited by 2

Built on by

Cited by year

Citing papers per year: 2025: 3.

3 papers.

  1. 2025B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Datacited by 4
  2. 2025Comprehensive Evaluation of Prototype Neural Networkscited by 1
  3. 2025XNNTab -- Interpretable Neural Networks for Tabular Data using Sparse Autoencoderscited by 0