mlsanityData to 13 Oct 2026

Towards the Characterization of Representations Learned via Capsule-based Network Architectures

arXiv 2305.05349 ↗First posted 9 May 2023cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Capsule Networks (CapsNets) have been re-introduced as a more compact and interpretable alternative to standard deep neural networks. While recent efforts have proved their compression capabilities, to date, their interpretability properties have not been fully assessed. Here, we conduct a systematic and principled study towards assessing the interpretability of these types of networks. Moreover, we pay special attention towards analyzing the level to which part-whole relationships are indeed encoded within the learned representation. Our analysis in the MNIST, SVHN, PASCAL-part and CelebA datasets suggest that the representations encoded in CapsNets might not be as disentangled nor strictly related to parts-whole relationships as is commonly stated in the literature.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 35 of its 61 references that are in the map. First posted on arXiv 9 May 2023.

Builds on

35 of 61 references.

References · 35

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,713
  2. 2014Deep Learning Face Attributes in the Wildcited by 3,686
  3. 2015Learning Deep Features for Discriminative Localizationcited by 2,434
  4. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,360
  5. 2013Visualizing and Understanding Convolutional Networkscited by 2,282
  6. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 707
  7. 2017Dynamic Routing Between Capsulescited by 689
  8. 2019MaskGAN: Towards Diverse and Interactive Facial Image Manipulationcited by 624
  9. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 611
  10. 2013Network In Networkcited by 603
  11. 2019A Survey of Deep Learning Techniques for Autonomous Drivingcited by 402
  12. 2019Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019cited by 273
23 more
  1. 2014Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Partscited by 231
  2. 2017Interpretable Convolutional Neural Networkscited by 161
  3. 2016Generating Visual Explanationscited by 158
  4. 2020Ground Truth Evaluation of Neural Network Explanations with CLEVR-XAIcited by 125
  5. 2019Stacked Capsule Autoencoderscited by 82
  6. 2021Efficient-CapsNet: Capsule Network with Self-Attention Routingcited by 41
  7. 2017Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networkscited by 28
  8. 2016Do semantic parts emerge in Convolutional Neural Networks?cited by 23
  9. 2019A Capsule Network for Recommendation and Explaining What You Like and Dislikecited by 16
  10. 2020Interpretable Graph Capsule Networks for Object Recognitioncited by 12
  11. 2018Text Classification using Capsulescited by 10
  12. 2018CapsNet comparative performance evaluation for image classificationcited by 9
  13. 2016A Taxonomy and Library for Visualizing Learned Features in Convolutional Neural Networkscited by 7
  14. 2018Dynamic Routing on Deep Neural Network for Thoracic Disease Classification and Sensitive Area Localizationcited by 7
  15. 2020iCaps: An Interpretable Classifier via Disentangled Capsule Networkscited by 7
  16. 2018Improved Explainability of Capsule Networks: Relevance Path by Agreementcited by 6
  17. 2023Why Capsule Neural Networks Do Not Scale: Challenging the Dynamic Parse-Tree Assumptioncited by 6
  18. 2020iCapsNets: Towards Interpretable Capsule Networks for Text Classificationcited by 4
  19. 2019Evaluating Generalization Ability of Convolutional Neural Networks and Capsule Networks for Image Classification via Top-2 Classificationcited by 3
  20. 2021Exploiting latent representation of sparse semantic layers for improved short-term motion prediction with Capsule Networkscited by 2
  21. 2018Capsule Networks for Protein Structure Classification and Predictioncited by 1
  22. 2019Path Capsule Networkscited by 1
  23. 2023On The Coherence of Quantitative Evaluation of Visual Explanationscited by 1

Built on by

Not cited yet.