mlsanityData to 7 Oct 2026

Dynamic Routing Between Capsules

arXiv 1710.09829 ↗First posted 26 Oct 2017cs.CVcited by 689

Not on the map. Why?

Abstract (arXiv)

A capsule is a group of neurons whose activity vector represents the instantiation parameters of a specific type of entity such as an object or an object part. We use the length of the activity vector to represent the probability that the entity exists and its orientation to represent the instantiation parameters. Active capsules at one level make predictions, via transformation matrices, for the instantiation parameters of higher-level capsules. When multiple predictions agree, a higher level capsule becomes active. We show that a discrimininatively trained, multi-layer capsule system achieves state-of-the-art performance on MNIST and is considerably better than a convolutional net at recognizing highly overlapping digits. To achieve these results we use an iterative routing-by-agreement mechanism: A lower-level capsule prefers to send its output to higher level capsules whose activity vectors have a big scalar product with the prediction coming from the lower-level capsule.

Key facts. Cited by 689 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Oct 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 209; 2022: 165; 2023: 105; 2024: 93; 2025: 74; 2026: 43.

689 papers.

Sort:

By area:

  1. 2021Dynamic Neural Networks: A Surveycited by 405
  2. 2021A Survey of Transformerscited by 399
  3. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 364
  4. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 259
  5. 2021Conditional Object-Centric Learning from Videocited by 247
  6. 2021Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domaincited by 241
  7. 2021ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Biascited by 216
  8. 2023DeepfakeBench: A Comprehensive Benchmark of Deepfake Detectioncited by 162
  9. 2021Explainable artificial intelligence (XAI) in deep learning-based medical image analysiscited by 147
  10. 2022LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Taskscited by 146
  11. 2021End-to-End Referring Video Object Segmentation with Multimodal Transformerscited by 135
  12. 2021Salient Object Detection via Integrity Learningcited by 133
38 more
  1. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  2. 2022Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networkscited by 126
  3. 2021How to represent part-whole hierarchies in a neural networkcited by 123
  4. 2021Generative Adversarial Transformerscited by 120
  5. 2021Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detectioncited by 119
  6. 2022ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyondcited by 117
  7. 2021Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyondcited by 116
  8. 2021DSelect-k: Differentiable Selection in the Mixture of Experts with Applications to Multi-Task Learningcited by 114
  9. 2022Disentangled Representation Learningcited by 111
  10. 2021Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factorscited by 106
  11. 2021Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learningcited by 100
  12. 2022Approximately Equivariant Networks for Imperfectly Symmetric Dynamicscited by 95
  13. 2021ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentationcited by 93
  14. 2021Achieving Forgetting Prevention and Knowledge Transfer in Continual Learningcited by 91
  15. 2021A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Conceptscited by 90
  16. 2021ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reductioncited by 84
  17. 2021Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methodscited by 83
  18. 2022Continual Learning of Natural Language Processing Tasks: A Surveycited by 83
  19. 2021Is Attention Better Than Matrix Decomposition?cited by 75
  20. 2023Deep Learning for Survival Analysis: A Reviewcited by 75
  21. 2023GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformerscited by 75
  22. 2023A Comprehensive Survey on Deep Graph Representation Learningcited by 72
  23. 2024MMPareto: Boosting Multimodal Learning with Innocent Unimodal Assistancecited by 72
  24. 2023iDisc: Internal Discretization for Monocular Depth Estimationcited by 71
  25. 2021Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domaincited by 70
  26. 2021Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularizationcited by 69
  27. 2022In Defense of the Unitary Scalarization for Deep Multi-Task Learningcited by 65
  28. 2022A General Survey on Attention Mechanisms in Deep Learningcited by 64
  29. 2021Multi-Task Learning in Natural Language Processing: An Overviewcited by 61
  30. 2023Concept Decomposition for Visual Exploration and Inspirationcited by 61
  31. 2021A Comprehensive Survey on Hardware-Aware Neural Architecture Searchcited by 60
  32. 2021Applications of Deep Learning in Fundus Images: A Reviewcited by 59
  33. 2021Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learningcited by 56
  34. 2021SA-Net: Shuffle Attention for Deep Convolutional Neural Networkscited by 54
  35. 2021Deep Gait Recognition: A Surveycited by 54
  36. 2021Convolutional Dynamic Alignment Networks for Interpretable Classificationscited by 54
  37. 2022Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Surveycited by 54
  38. 2022Dynamic Multimodal Fusioncited by 54

50 most cited of 689 All 689 (JSON)