mlsanityData to 7 Oct 2026

FICNN: A Framework for the Interpretation of Deep Convolutional Neural Networks

arXiv 2305.10121 ↗First posted 17 May 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

With the continue development of Convolutional Neural Networks (CNNs), there is a growing concern regarding representations that they encode internally. Analyzing these internal representations is referred to as model interpretation. While the task of model explanation, justifying the predictions of such models, has been studied extensively; the task of model interpretation has received less attention. The aim of this paper is to propose a framework for the study of interpretation methods designed for CNN models trained from visual data. More specifically, we first specify the difference between the interpretation and explanation tasks which are often considered the same in the literature. Then, we define a set of six specific factors that can be used to characterize interpretation methods. Third, based on the previous factors, we propose a framework for the positioning of interpretation methods. Our framework highlights that just a very small amount of the suggested factors, and combinations thereof, have been actually studied. Consequently, leaving significant areas unexplored. Following the proposed framework, we discuss existing interpretation methods and give some attention to the evaluation protocols followed to validate them. Finally, the paper highlights capabilities of the methods in producing feedback for enabling interpretation and proposes possible research problems arising from the framework.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 40 of its 66 references that are in the map. First posted on arXiv 17 May 2023.

Builds on

40 of 66 references.

References · 40

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  3. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  4. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
  5. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  6. 2016Understanding intermediate layers using linear classifier probescited by 1,279
  7. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  8. 2019Attention is not Explanationcited by 916
  9. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  10. 2017Dynamic Routing Between Capsulescited by 689
  11. 2018Explaining Explanations: An Overview of Interpretability of Machine Learningcited by 508
  12. 2014Understanding Deep Image Representations by Inverting Themcited by 399
28 more
  1. 2020A Survey on Neural Network Interpretabilitycited by 291
  2. 2017Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictionscited by 234
  3. 2020Concept Whitening for Interpretable Image Recognitioncited by 225
  4. 2020Neural Prototype Trees for Interpretable Fine-grained Image Recognitioncited by 213
  5. 2014Object Detectors Emerge in Deep Scene CNNscited by 178
  6. 2020Compositional Explanations of Neuronscited by 172
  7. 2015Inverting Visual Representations with Convolutional Networkscited by 168
  8. 2017Interpretable Convolutional Neural Networkscited by 161
  9. 2020Attribute Prototype Network for Zero-Shot Learningcited by 160
  10. 2018Visual Interpretability for Deep Learning: a Surveycited by 155
  11. 2018Net2Vec: Quantifying and Explaining how Concepts are Encoded by Filters in Deep Neural Networkscited by 128
  12. 2021Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypescited by 120
  13. 2020Invertible Concept-based Explanations for CNN Models with Non-negative Concept Activation Vectorscited by 119
  14. 2021Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyondcited by 116
  15. 2017Interpreting Deep Visual Representations via Network Dissectioncited by 103
  16. 2018Grounding Visual Explanationscited by 92
  17. 2018Interpreting CNNs via Decision Treescited by 89
  18. 2020ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discoverycited by 89
  19. 2018GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentationcited by 40
  20. 2017Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networkscited by 28
  21. 2015Understanding Intra-Class Knowledge Inside CNNcited by 22
  22. 2013Dictionary Learning and Sparse Coding on Grassmann Manifolds: An Extrinsic Solutioncited by 13
  23. 2021Latent Space Explanation by Interventioncited by 13
  24. 2017Understanding trained CNNs by indexing neuron selectivitycited by 12
  25. 2021PACE: Posthoc Architecture-Agnostic Concept Extractor for Explaining CNNscited by 12
  26. 2022Measuring the Interpretability of Unsupervised Representations via Quantized Reverse Probingcited by 8
  27. 2016A Taxonomy and Library for Visualizing Learned Features in Convolutional Neural Networkscited by 7
  28. 2015Mining Mid-level Visual Patterns with Deep CNN Activationscited by 1

Built on by

Not cited yet.