mlsanityData to 14 Oct 2026

Interpretable Image Classification with Differentiable Prototypes Assignment

arXiv 2112.02902 ↗First posted 6 Dec 2021cs.CV cs.AI cs.LGcited by 97

Not on the map. Why?

Abstract (arXiv)

We introduce ProtoPool, an interpretable image classification model with a pool of prototypes shared by the classes. The training is more straightforward than in the existing methods because it does not require the pruning stage. It is obtained by introducing a fully differentiable assignment of prototypes to particular classes. Moreover, we introduce a novel focal similarity function to focus the model on the rare foreground features. We show that ProtoPool obtains state-of-the-art accuracy on the CUB-200-2011 and the Stanford Cars datasets, substantially reducing the number of prototypes. We provide a theoretical analysis of the method and a user study to show that our prototypes are more distinctive than those obtained with competitive methods.

Key facts. Cited by 97 papers in the map (data through 14 Oct 2026). Builds on 42 of its 67 references that are in the map. First posted on arXiv 6 Dec 2021.

Builds on

42 of 67 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  4. 2016Densely Connected Convolutional Networkscited by 6,720
  5. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  6. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  7. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  8. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  9. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  10. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
  11. 2018Sanity Checks for Saliency Mapscited by 1,156
  12. 2020Concept Bottleneck Modelscited by 1,032
30 more
  1. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 737
  2. 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 614
  3. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 612
  4. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  5. 2019Counterfactual Visual Explanationscited by 313
  6. 2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 305
  7. 2020Counterfactual VQA: A Cause-Effect Look at Language Biascited by 266
  8. 2019Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNetcited by 260
  9. 2019Understanding Deep Networks via Extremal Perturbations and Smooth Maskscited by 259
  10. 2019On Completeness-aware Concept-Based Explanations in Deep Neural Networkscited by 239
  11. 2017Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictionscited by 234
  12. 2020Concept Whitening for Interpretable Image Recognitioncited by 225
  13. 2020Neural Prototype Trees for Interpretable Fine-grained Image Recognitioncited by 214
  14. 2021Visual Saliency Transformercited by 175
  15. 2019Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Groundedcited by 128
  16. 2021ProtGNN: Towards Self-Explaining Graph Neural Networkscited by 96
  17. 2019Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognitioncited by 95
  18. 2020ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discoverycited by 89
  19. 2021XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanationscited by 73
  20. 2019Interpretable and Steerable Sequence Learning via Prototypescited by 72
  21. 2021IAIA-BL: A Case-based Interpretable Deep Learning Model for Classification of Mass Lesions in Digital Mammographycited by 72
  22. 2014The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classificationcited by 67
  23. 2019Interpretable Image Recognition with Hierarchical Prototypescited by 65
  24. 2021This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networkscited by 65
  25. 2020There and Back Again: Revisiting Backpropagation Saliency Methodscited by 60
  26. 2020SCOUT: Self-aware Discriminant Counterfactual Explanationscited by 52
  27. 2020This Looks Like That, Because ... Explaining Prototypes for Interpretable Image Recognitioncited by 50
  28. 2019Explaining Deep Classification of Time-Series Data with Learned Prototypescited by 30
  29. 2020Interpretable Deep Models for Cardiac Resynchronisation Therapy Response Predictioncited by 17
  30. 2019Semantically Interpretable Activation Maps: what-where-how explanations within CNNscited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 4; 2023: 27; 2024: 28; 2025: 27; 2026: 11.

97 papers.

Sort:

By area:

  1. 2022Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networkscited by 129
  2. 2023Concept-based Explainable Artificial Intelligence: A Surveycited by 98
  3. 2023Adversarial attacks and defenses in explainable artificial intelligence: A surveycited by 48
  4. 2023Adversarial Counterfactual Visual Explanationscited by 47
  5. 2023Learning Support and Trivial Prototypes for Interpretable Image Classificationcited by 38
  6. 2022Evaluation and Improvement of Interpretability for Self-Explainable Part-Prototype Networkscited by 37
  7. 2023This Looks Like Those: Illuminating Prototypical Concepts Using Multiple Visualizationscited by 36
  8. 2023ProtoSeg: Interpretable Semantic Segmentation with Prototypical Partscited by 33
  9. 2023Interpretability Benchmark for Evaluating Spatial Misalignment of Prototypical Parts Explanationscited by 27
  10. 2024Interpretable Image Classification with Adaptive Prototype-based Vision Transformerscited by 25
  11. 2023ICICLE: Interpretable Class Incremental Continual Learningcited by 24
  12. 2024On the Concept Trustworthiness in Concept Bottleneck Modelscited by 22
38 more
  1. 2023Pixel-Grounded Prototypical Part Networkscited by 18
  2. 2024Self-eXplainable AI for Medical Image Analysis: A Survey and New Outlookscited by 18
  3. 2025A Comprehensive Survey on Self-Interpretable Neural Networkscited by 18
  4. 2023The Co-12 Recipe for Evaluating Interpretable Part-Prototype Image Classifierscited by 15
  5. 2024LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Visioncited by 15
  6. 2023MProtoNet: A Case-Based Interpretable Model for Brain Tumor Classification with 3D Multi-parametric Magnetic Resonance Imagingcited by 11
  7. 2023Interpreting and Correcting Medical Image Classification with PIP-Netcited by 11
  8. 2023On the Interpretability of Part-Prototype Based Classifiers: A Human Centric Analysiscited by 11
  9. 2023Mixture of Gaussian-distributed Prototypes with Generative Modelling for Interpretable and Trustworthy Image Recognitioncited by 11
  10. 2024Explainable AI (XAI) in Image Segmentation in Medicine, Industry, and Beyond: A Surveycited by 11
  11. 2024This Looks Better than That: Better Interpretable Models with ProtoPNeXtcited by 11
  12. 2025Interactive Medical Image Analysis with Concept-based Similarity Reasoningcited by 11
  13. 2025Interpretable Image Classification via Non-parametric Part Prototype Learningcited by 11
  14. 2023I-AI: A Controllable & Interpretable AI System for Decoding Radiologists' Intense Focus for Accurate CXR Diagnosescited by 10
  15. 2024MCPNet: An Interpretable Classifier via Multi-Level Concept Prototypescited by 10
  16. 2024AudioProtoPNet: An interpretable deep learning model for bird sound classificationcited by 10
  17. 2023Q-SENN: Quantized Self-Explaining Neural Networkscited by 9
  18. 2022ProGReST: Prototypical Graph Regression Soft Trees for Molecular Property Predictioncited by 8
  19. 2023Sanity checks for patch visualisation in prototype-based image classificationcited by 8
  20. 2024ProtoS-ViT: Visual foundation models for sparse self-explainable classificationscited by 8
  21. 2024InfoDisent: Explainability of Image Classification Models by Information Disentanglementcited by 8
  22. 2023Take 5: Interpretable Image Classification with a Handful of Featurescited by 7
  23. 2023Concept-Centric Transformers: Enhancing Model Interpretability through Object-Centric Concept Learning within a Shared Global Workspacecited by 7
  24. 2023ProtoArgNet: Interpretable Image Classification with Super-Prototypes and Argumentation [Technical Report]cited by 7
  25. 2024Post-hoc Part-prototype Networkscited by 7
  26. 2023Prototypical Self-Explainable Models Without Re-trainingcited by 6
  27. 2025SUB: Benchmarking CBM Generalization via Synthetic Attribute Substitutionscited by 6
  28. 2025Geodesic Prototype Matching via Diffusion Maps for Interpretable Fine-Grained Recognitioncited by 6
  29. 2024An Overview of Prototype Formulations for Interpretable Deep Learningcited by 5
  30. 2025Formal Abductive Latent Explanations for Prototype-Based Networkscited by 5
  31. 2025SIDE: Sparse Information Disentanglement for Explainable Artificial Intelligencecited by 4
  32. 2023Sanity checks and improvements for patch visualisation in prototype-based image classificationcited by 3
  33. 2023PCNN: Probable-Class Nearest-Neighbor Explanations Improve Fine-Grained Image Classification Accuracy for AIs and Humanscited by 3
  34. 2024PIPNet3D: Interpretable Detection of Alzheimer in MRI Scanscited by 3
  35. 2024Prototype-based Interpretable Breast Cancer Prediction Models: Analysis and Challengescited by 3
  36. 2024Semantic Prototypes: Enhancing Transparency Without Black Boxescited by 3
  37. 2024CaBRNet, an open-source library for developing and evaluating Case-Based Reasoning Modelscited by 3
  38. 2025This looks like what? Challenges and Future Research Directions for Part-Prototype Modelscited by 3

50 most cited of 97 All 97 (JSON)