mlsanityData to 7 Oct 2026

ICICLE: Interpretable Class Incremental Continual Learning

arXiv 2303.07811 ↗First posted 14 Mar 2023cs.LG cs.AI cs.CVcited by 24

Not on the map. Why?

Abstract (arXiv)

Continual learning enables incremental learning of new tasks without forgetting those previously learned, resulting in positive knowledge transfer that can enhance performance on both new and old tasks. However, continual learning poses new challenges for interpretability, as the rationale behind model predictions may change over time, leading to interpretability concept drift. We address this problem by proposing Interpretable Class-InCremental LEarning (ICICLE), an exemplar-free approach that adopts a prototypical part-based approach. It consists of three crucial novelties: interpretability regularization that distills previously learned concepts while preserving user-friendly positive reasoning; proximity-based prototype initialization strategy dedicated to the fine-grained setting; and task-recency bias compensation devoted to prototypical parts. Our experimental results demonstrate that ICICLE reduces the interpretability concept drift and outperforms the existing exemplar-free methods of common class-incremental learning when applied to concept-based models.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 69 of its 99 references that are in the map. First posted on arXiv 14 Mar 2023.

Builds on

69 of 99 references.

References · 69

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  5. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  6. 2016Learning without Forgettingcited by 2,465
  7. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  8. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  9. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  10. 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,094
  11. 2018Efficient Lifelong Learning with A-GEMcited by 1,044
  12. 2020Concept Bottleneck Modelscited by 1,022
38 more
  1. 2017PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruningcited by 882
  2. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 734
  3. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  4. 2019Large Scale Incremental Learningcited by 727
  5. 2013An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networkscited by 711
  6. 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 698
  7. 2018Overcoming catastrophic forgetting with hard attention to the taskcited by 672
  8. 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 612
  9. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 611
  10. 2019Three scenarios for continual learningcited by 610
  11. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  12. 2020Class-incremental learning: survey and performance evaluation on image classificationcited by 446
  13. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 364
  14. 2021DER: Dynamically Expandable Representation for Class Incremental Learningcited by 355
  15. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 337
  16. 2019Counterfactual Visual Explanationscited by 312
  17. 2021Rainbow Memory: Continual Learning with a Memory of Diverse Samplescited by 273
  18. 2020Counterfactual VQA: A Cause-Effect Look at Language Biascited by 266
  19. 2019Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNetcited by 260
  20. 2019Understanding Deep Networks via Extremal Perturbations and Smooth Maskscited by 257
  21. 2018Learning without Memorizingcited by 249
  22. 2020Semantic Drift Compensation for Class-Incremental Learningcited by 241
  23. 2019On Completeness-aware Concept-Based Explanations in Deep Neural Networkscited by 239
  24. 2017Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictionscited by 234
  25. 2020Concept Whitening for Interpretable Image Recognitioncited by 225
  26. 2020Neural Prototype Trees for Interpretable Fine-grained Image Recognitioncited by 213
  27. 2020Making deep neural networks right for the right scientific reasons by interacting with their explanationscited by 141
  28. 2018Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgettingcited by 127
  29. 2019Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Groundedcited by 127
  30. 2021Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypescited by 120
  31. 2022FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learningcited by 120
  32. 2021Distilling Causal Effect of Data in Class-Incremental Learningcited by 117
  33. 2021HIVE: Evaluating the Human Interpretability of Visual Explanationscited by 105
  34. 2021Recent advances and clinical applications of deep learning in medical image analysiscited by 104
  35. 2021Interpretable Image Classification with Differentiable Prototypes Assignmentcited by 97
  36. 2021ProtGNN: Towards Self-Explaining Graph Neural Networkscited by 96
  37. 2020ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discoverycited by 89
  38. 2022B-cos Networks: Alignment is All We Need for Interpretabilitycited by 88

50 most cited of 69 All 69 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 6; 2025: 8; 2026: 5.

24 papers.

Sort:

By area:

  1. 2024Resurrecting Old Classes with New Data for Exemplar-Free Continual Learningcited by 33
  2. 2025Language Guided Concept Bottleneck Models for Interpretable Continual Learningcited by 28
  3. 2023Interpretability Benchmark for Evaluating Spatial Misalignment of Prototypical Parts Explanationscited by 27
  4. 2023Continual Learning in Medical Image Analysis: A Comprehensive Review of Recent Advancements and Future Prospectscited by 22
  5. 2025A Comprehensive Survey on Self-Interpretable Neural Networkscited by 18
  6. 2024LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Visioncited by 15
  7. 2025Task-Agnostic Guided Feature Expansion for Class-Incremental Learningcited by 15
  8. 2025Rashomon Sets for Prototypical-Part Networks: Editing Interpretable Models in Real-Timecited by 13
  9. 2024Continual Learning on Graphs: A Surveycited by 11
  10. 2024Continual Learning for Smart City: A Surveycited by 9
  11. 2023Read Between the Layers: Leveraging Multi-Layer Representations for Rehearsal-Free Continual Learning with Pre-Trained Modelscited by 7
  12. 2024InfoDisent: Explainability of Image Classification Models by Information Disentanglementcited by 7
12 more
  1. 2026Position: Modular Memory is the Key to Continual Learning Agentscited by 7
  2. 2024Reconstruct before Query: Continual Missing Modality Learning with Decomposed Prompt Collaborationcited by 4
  3. 2025This looks like what? Challenges and Future Research Directions for Part-Prototype Modelscited by 3
  4. 2025SIDE: Sparse Information Disentanglement for Explainable Artificial Intelligencecited by 3
  5. 2023A Protocol for Continual Explanation of SHAPcited by 2
  6. 2023TORE: Token Recycling in Vision Transformers for Efficient Active Visual Explorationcited by 2
  7. 2025Walking the Web of Concept-Class Relationships in Incrementally Trained Interpretable Modelscited by 1
  8. 2025CIP-Net: Continual Interpretable Prototype-based Networkcited by 0
  9. 2026ProtoQuant: Quantization of Prototypical Parts For General and Fine-Grained Image Classificationcited by 0
  10. 2026CI-CBM: Class-Incremental Concept Bottleneck Model for Interpretable Continual Learningcited by 0
  11. 2026Online Continual Learning with Dynamic Label Hierarchiescited by 0
  12. 2026Challenges of Explainability in Continual Learning for Time Series Forecastingcited by 0