mlsanityData to 7 Oct 2026

InfoDisent: Explainability of Image Classification Models by Information Disentanglement

arXiv 2409.10329 ↗First posted 16 Sep 2024cs.CV cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

In this work, we introduce InfoDisent, a hybrid approach to explainability based on the information bottleneck principle. InfoDisent enables the disentanglement of information in the final layer of any pretrained model into atomic concepts, which can be interpreted as prototypical parts. This approach merges the flexibility of post-hoc methods with the concept-level modeling capabilities of self-explainable neural networks, such as ProtoPNets. We demonstrate the effectiveness of InfoDisent through computational experiments and user studies across various datasets using modern backbones such as ViTs and convolutional networks. Notably, InfoDisent generalizes the prototypical parts approach to novel domains (ImageNet).

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 31 of its 51 references that are in the map. First posted on arXiv 16 Sep 2024.

Builds on

31 of 51 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  6. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  7. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  8. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  9. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  10. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
  11. 2018Sanity Checks for Saliency Mapscited by 1,149
  12. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
19 more
  1. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  2. 2020Transformer Interpretability Beyond Attention Visualizationcited by 620
  3. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  4. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 299
  5. 2016Not Just a Black Box: Learning Important Features Through Propagating Activation Differencescited by 295
  6. 2019Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNetcited by 260
  7. 2021Visual Saliency Transformercited by 175
  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. 2019Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognitioncited by 95
  12. 2020ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discoverycited by 89
  13. 2022B-cos Networks: Alignment is All We Need for Interpretabilitycited by 88
  14. 2017Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Carcited by 65
  15. 2023FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methodscited by 49
  16. 2021Fast Axiomatic Attribution for Neural Networkscited by 35
  17. 2022Explainable Deep Learning Methods in Medical Image Classification: A Surveycited by 31
  18. 2023ICICLE: Interpretable Class Incremental Continual Learningcited by 24
  19. 2024LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Visioncited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 5.

7 papers.

  1. 2025EPIC: Explanation of Pretrained Image Classification Networks via Prototypecited by 6
  2. 2025SIDE: Sparse Information Disentanglement for Explainable Artificial Intelligencecited by 3
  3. 2026ProtoQuant: Quantization of Prototypical Parts For General and Fine-Grained Image Classificationcited by 0
  4. 2026XSPLAIN: XAI-enabling Splat-based Prototype Learning for Attribute-aware INterpretabilitycited by 0
  5. 2026ProDG: Prototypes for Data-Free Generative Post-Hoc Explainabilitycited by 0
  6. 2026Conceptualizing Embeddings: Sparse Disentanglement for Vision-Language Modelscited by 0
  7. 2026DisParQ: Self-Supervised Part Concepts for Interpretable Vision Foundation Modelscited by 0