mlsanityData to 14 Oct 2026

This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagation

arXiv 2108.12204 ↗First posted 27 Aug 2021cs.LGcited by 43

Not on the map. Why?

Abstract (arXiv)

Current machine learning models have shown high efficiency in solving a wide variety of real-world problems. However, their black box character poses a major challenge for the understanding and traceability of the underlying decision-making strategies. As a remedy, many post-hoc explanation and self-explanatory methods have been developed to interpret the models' behavior. These methods, in addition, enable the identification of artifacts that can be learned by the model as class-relevant features. In this work, we provide a detailed case study of the self-explaining network, ProtoPNet, in the presence of a spectrum of artifacts. Accordingly, we identify the main drawbacks of ProtoPNet, especially, its coarse and spatially imprecise explanations. We address these limitations by introducing Prototypical Relevance Propagation (PRP), a novel method for generating more precise model-aware explanations. Furthermore, in order to obtain a clean dataset, we propose to use multi-view clustering strategies for segregating the artifact images using the PRP explanations, thereby suppressing the potential artifact learning in the models.

Key facts. Cited by 43 papers in the map (data through 14 Oct 2026). Builds on 41 of its 78 references that are in the map. First posted on arXiv 27 Aug 2021.

Builds on

41 of 78 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  5. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  6. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  7. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 737
  8. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  9. 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 456
  10. 2019A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAIcited by 404
  11. 2019Unmasking Clever Hans Predictors and Assessing What Machines Really Learncited by 365
  12. 2014Recurrent Models of Visual Attentioncited by 349
29 more
  1. 2017Methods for Interpreting and Understanding Deep Neural Networkscited by 345
  2. 2015Understanding Neural Networks Through Deep Visualizationcited by 334
  3. 2017Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictionscited by 234
  4. 2020Concept Whitening for Interpretable Image Recognitioncited by 225
  5. 2016On Deep Multi-View Representation Learning: Objectives and Optimizationcited by 162
  6. 2017Interpretable Convolutional Neural Networkscited by 162
  7. 2020Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Reviewcited by 123
  8. 2019When Explanations Lie: Why Many Modified BP Attributions Failcited by 92
  9. 2017Learning how to explain neural networks: PatternNet and PatternAttributioncited by 84
  10. 2021XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanationscited by 73
  11. 2019Towards Best Practice in Explaining Neural Network Decisions with LRPcited by 70
  12. 2019Interpretable Image Recognition with Hierarchical Prototypescited by 65
  13. 2020Explanation-Guided Training for Cross-Domain Few-Shot Classificationcited by 58
  14. 2021Reconsidering Representation Alignment for Multi-view Clusteringcited by 57
  15. 2019Saccader: Improving Accuracy of Hard Attention Models for Visioncited by 35
  16. 2019From Clustering to Cluster Explanations via Neural Networkscited by 34
  17. 2018Towards Explaining Anomalies: A Deep Taylor Decomposition of One-Class Modelscited by 24
  18. 2019A Rate-Distortion Framework for Explaining Neural Network Decisionscited by 24
  19. 2020A Framework to Learn with Interpretationcited by 23
  20. 2020How Much Can I Trust You? -- Quantifying Uncertainties in Explaining Neural Networkscited by 18
  21. 2019Deep Divergence-Based Approach to Clusteringcited by 13
  22. 2019EDUCE: Explaining model Decisions through Unsupervised Concepts Extractioncited by 13
  23. 2017AOGNets: Compositional Grammatical Architectures for Deep Learningcited by 6
  24. 2018Unsupervised Learning of Neural Networks to Explain Neural Networkscited by 6
  25. 2020GraphXCOVID: Explainable Deep Graph Diffusion Pseudo-Labelling for Identifying COVID-19 on Chest X-rayscited by 6
  26. 2016Feature Importance Measure for Non-linear Learning Algorithmscited by 5
  27. 2019Analyzing the Interpretability Robustness of Self-Explaining Modelscited by 5
  28. 2019Finding and Removing Clever Hans: Using Explanation Methods to Debug and Improve Deep Modelscited by 5
  29. 2019Unsupervised Learning of Neural Networks to Explain Neural Networks (extended abstract)cited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 8; 2023: 13; 2024: 14; 2025: 5; 2026: 3.

43 papers.

Sort:

By area:

  1. 2022ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognitioncited by 63
  2. 2022Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvementcited by 48
  3. 2022ProtoVAE: A Trustworthy Self-Explainable Prototypical Variational Modelcited by 34
  4. 2023Finding the right XAI method -- A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Sciencecited by 27
  5. 2023Interpretability Benchmark for Evaluating Spatial Misalignment of Prototypical Parts Explanationscited by 27
  6. 2022Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspacescited by 25
  7. 2023ICICLE: Interpretable Class Incremental Continual Learningcited by 24
  8. 2023Explainable AI for Time Series via Virtual Inspection Layerscited by 23
  9. 2023Pixel-Grounded Prototypical Part Networkscited by 18
  10. 2022ECLAD: Extracting Concepts with Local Aggregated Descriptorscited by 15
  11. 2023The Co-12 Recipe for Evaluating Interpretable Part-Prototype Image Classifierscited by 15
  12. 2024LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Visioncited by 15
31 more
  1. 2022DORA: Exploring Outlier Representations in Deep Neural Networkscited by 14
  2. 2024Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspectivecited by 9
  3. 2024PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformerscited by 9
  4. 2023Sanity checks for patch visualisation in prototype-based image classificationcited by 8
  5. 2024ProtoS-ViT: Visual foundation models for sparse self-explainable classificationscited by 8
  6. 2024This actually looks like that: Proto-BagNets for local and global interpretability-by-designcited by 7
  7. 2023Prototypical Self-Explainable Models Without Re-trainingcited by 6
  8. 2022Demonstrating The Risk of Imbalanced Datasets in Chest X-ray Image-based Diagnostics by Prototypical Relevance Propagationcited by 5
  9. 2023ProtoExplorer: Interpretable Forensic Analysis of Deepfake Videos using Prototype Exploration and Refinementcited by 5
  10. 2025DocVXQA: Context-Aware Visual Explanations for Document Question Answeringcited by 5
  11. 2022Towards Human-Interpretable Prototypes for Visual Assessment of Image Classification Modelscited by 4
  12. 2024Pantypes: Diverse Representatives for Self-Explainable Modelscited by 4
  13. 2023Sanity checks and improvements for patch visualisation in prototype-based image classificationcited by 3
  14. 2023Interpretable Alzheimer's Disease Classification Via a Contrastive Diffusion Autoencodercited by 3
  15. 2024PIPNet3D: Interpretable Detection of Alzheimer in MRI Scanscited by 3
  16. 2024Prototype-based Interpretable Breast Cancer Prediction Models: Analysis and Challengescited by 3
  17. 2024This Probably Looks Exactly Like That: An Invertible Prototypical Networkcited by 3
  18. 2024CaBRNet, an open-source library for developing and evaluating Case-Based Reasoning Modelscited by 3
  19. 2025This looks like what? Challenges and Future Research Directions for Part-Prototype Modelscited by 3
  20. 2023PAMI: partition input and aggregate outputs for model interpretationcited by 2
  21. 2023A differentiable Gaussian Prototype Layer for explainable Segmentationcited by 2
  22. 2024Beyond explaining: XAI-based Adaptive Learning with SHAP Clustering for Energy Consumption Predictioncited by 2
  23. 2024OMENN: One Matrix to Explain Neural Networkscited by 2
  24. 2024Applications of Explainable artificial intelligence in Earth system sciencecited by 1
  25. 2025Comprehensive Evaluation of Prototype Neural Networkscited by 1
  26. 2025CIP-Net: Continual Interpretable Prototype-based Networkcited by 1
  27. 2024Enhancing Interpretability of Vertebrae Fracture Grading using Human-interpretable Prototypescited by 0
  28. 2025ProtoMask: Segmentation-Guided Prototype Learningcited by 0
  29. 2026A New Framework to Analyse the Distributional Robustness of Deep Neural Networkscited by 0
  30. 2026Self-Explainability in Self-Adaptive and Self-Organising Systems: Status and Research Directionscited by 0
  31. 2026ProtoX-AD: Self-Explainable Time Series Anomaly Detection and Characterizationcited by 0