mlsanityData to 7 Oct 2026

Representational Similarity via Interpretable Visual Concepts

arXiv 2503.15699 ↗First posted 19 Mar 2025cs.CV cs.AI q-bio.NCcited by 5

Not on the map. Why?

Abstract (arXiv)

How do two deep neural networks differ in how they arrive at a decision? Measuring the similarity of deep networks has been a long-standing open question. Most existing methods provide a single number to measure the similarity of two networks at a given layer, but give no insight into what makes them similar or dissimilar. We introduce an interpretable representational similarity method (RSVC) to compare two networks. We use RSVC to discover shared and unique visual concepts between two models. We show that some aspects of model differences can be attributed to unique concepts discovered by one model that are not well represented in the other. Finally, we conduct extensive evaluation across different vision model architectures and training protocols to demonstrate its effectiveness.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 42 of its 61 references that are in the map. First posted on arXiv 19 Mar 2025.

Builds on

42 of 61 references.

References · 42

  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. 2023GPT-4 Technical Reportcited by 18,132
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  5. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  6. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  7. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  8. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  9. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  10. 2019Similarity of Neural Network Representations Revisitedcited by 1,695
  11. 2023Sparse Autoencoders Find Highly Interpretable Features in Language Modelscited by 1,359
  12. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
30 more
  1. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  2. 2021Do Vision Transformers See Like Convolutional Neural Networks?cited by 671
  3. 2020What is being transferred in transfer learning?cited by 365
  4. 2024The Platonic Representation Hypothesiscited by 362
  5. 2020Understanding the Role of Individual Units in a Deep Neural Networkcited by 254
  6. 2020Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depthcited by 241
  7. 2015Convergent Learning: Do different neural networks learn the same representations?cited by 215
  8. 2023Interpreting CLIP's Image Representation via Text-Based Decompositioncited by 189
  9. 2022Datamodels: Predicting Predictions from Training Datacited by 186
  10. 2022CRAFT: Concept Recursive Activation FacTorization for Explainabilitycited by 177
  11. 2022From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagationcited by 141
  12. 2023Similarity of Neural Network Models: A Survey of Functional and Representational Measurescited by 128
  13. 2020Invertible Concept-based Explanations for CNN Models with Non-negative Concept Activation Vectorscited by 119
  14. 2022Revealing the Dark Secrets of Masked Image Modelingcited by 117
  15. 2023A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimationcited by 108
  16. 2023Concept-based Explainable Artificial Intelligence: A Surveycited by 97
  17. 2022Human alignment of neural network representationscited by 74
  18. 2022Harmonizing the object recognition strategies of deep neural networks with humanscited by 59
  19. 2019Unsupervised Model Selection for Variational Disentangled Representation Learningcited by 46
  20. 2023Rosetta Neurons: Mining the Common Units in a Model Zoocited by 46
  21. 2022Disentanglement of Correlated Factors via Hausdorff Factorized Supportcited by 37
  22. 2018Celer: a Fast Solver for the Lasso with Dual Extrapolationcited by 31
  23. 2022ModelDiff: A Framework for Comparing Learning Algorithmscited by 30
  24. 2022Xplique: A Deep Learning Explainability Toolboxcited by 24
  25. 2022DCI-ES: An Extended Disentanglement Framework with Connections to Identifiabilitycited by 23
  26. 2021Best of both worlds: local and global explanations with human-understandable conceptscited by 22
  27. 2024Understanding Video Transformers via Universal Concept Discoverycited by 22
  28. 2021Efficient Diversity-Driven Ensemble for Deep Neural Networkscited by 11
  29. 2024How Aligned are Different Alignment Metrics?cited by 6
  30. 2023Training-Free Uncertainty Estimation for Embedding Modelscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 2.

5 papers.

  1. 2025Superposition disentanglement of neural representations reveals hidden alignmentcited by 4
  2. 2026Does AI See like Art Historians? Interpreting How Vision Language Models Recognize Artistic Stylecited by 3
  3. 2025Measuring the (Un)Faithfulness of Concept-Based Explanationscited by 1
  4. 2025Representational Difference Explanationscited by 0
  5. 2026Feature Evolution and Migration during Vision Transformer Trainingcited by 0