mlsanityData to 7 Oct 2026

ProtoArgNet: Interpretable Image Classification with Super-Prototypes and Argumentation [Technical Report]

arXiv 2311.15438 ↗First posted 26 Nov 2023cs.CV cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

We propose ProtoArgNet, a novel interpretable deep neural architecture for image classification in the spirit of prototypical-part-learning as found, e.g., in ProtoPNet. While earlier approaches associate every class with multiple prototypical-parts, ProtoArgNet uses super-prototypes that combine prototypical-parts into a unified class representation. This is done by combining local activations of prototypes in an MLP-like manner, enabling the localization of prototypes and learning (non-linear) spatial relationships among them. By leveraging a form of argumentation, ProtoArgNet is capable of providing both supporting (i.e. `this looks like that') and attacking (i.e. `this differs from that') explanations. We demonstrate on several datasets that ProtoArgNet outperforms state-of-the-art prototypical-part-learning approaches. Moreover, the argumentation component in ProtoArgNet is customisable to the user's cognitive requirements by a process of sparsification, which leads to more compact explanations compared to state-of-the-art approaches.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 27 of its 55 references that are in the map. First posted on arXiv 26 Nov 2023.

Builds on

27 of 55 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  6. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  7. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  8. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  9. 2019Neural Probabilistic Logic Programming in DeepProbLogcited by 389
  10. 2019Counterfactual Visual Explanationscited by 312
  11. 2017Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictionscited by 234
  12. 2020Neural Prototype Trees for Interpretable Fine-grained Image Recognitioncited by 213
15 more
  1. 2017Learning to Reason: End-to-End Module Networks for Visual Question Answeringcited by 125
  2. 2021Interpretable Image Classification with Differentiable Prototypes Assignmentcited by 97
  3. 2017Logic Tensor Networks for Semantic Image Interpretationcited by 92
  4. 2020ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discoverycited by 89
  5. 2017Measuring the tendency of CNNs to Learn Surface Statistical Regularitiescited by 87
  6. 2021XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanationscited by 72
  7. 2021Argumentative XAI: A Surveycited by 66
  8. 2021This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networkscited by 65
  9. 2020Interpreting Neural Networks as Gradual Argumentation Frameworks (Including Proof Appendix)cited by 38
  10. 2023Learning Support and Trivial Prototypes for Interpretable Image Classificationcited by 38
  11. 2021DISSECT: Disentangled Simultaneous Explanations via Concept Traversalscited by 37
  12. 2022Deep Symbolic Learning: Discovering Symbols and Rules from Perceptionscited by 20
  13. 2023SpArX: Sparse Argumentative Explanations for Neural Networks [Technical Report]cited by 18
  14. 2021Integrated Grad-CAM: Sensitivity-Aware Visual Explanation of Deep Convolutional Networks via Integrated Gradient-Based Scoringcited by 16
  15. 2023Explain What You See: Open-Ended Segmentation and Recognition of Occluded 3D Objectscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 3.

7 papers.

  1. 2025Geodesic Prototype Matching via Diffusion Maps for Interpretable Fine-Grained Recognitioncited by 6
  2. 2025Neuro-Argumentative Learning with Case-Based Reasoningcited by 3
  3. 2026This Looks Distinctly Like That: Grounding Interpretable Recognition in Stiefel Geometry against Neural Collapsecited by 1
  4. 2025ILLC: Iterative Layer-by-Layer Compression for Enhancing Structural Faithfulness in SpArXcited by 0
  5. 2025Multimodal Feature Prototype Learning for Interpretable and Discriminative Cancer Survival Predictioncited by 0
  6. 2026Deep Arguingcited by 0
  7. 2026Beyond L2: Generalizing Abductive Latent Explanations to Diverse Prototype-Based Architecturescited by 0