mlsanityData to 7 Oct 2026

Visualizing and Understanding Convolutional Networks

arXiv 1311.2901 ↗First posted 12 Nov 2013cs.CVcited by 2,278

Not on the map. Why?

Cited by 27 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Large Convolutional Network models have recently demonstrated impressive classification performance on the ImageNet benchmark. However there is no clear understanding of why they perform so well, or how they might be improved. In this paper we address both issues. We introduce a novel visualization technique that gives insight into the function of intermediate feature layers and the operation of the classifier. We also perform an ablation study to discover the performance contribution from different model layers. This enables us to find model architectures that outperform Krizhevsky etal on the ImageNet classification benchmark. We show our ImageNet model generalizes well to other datasets: when the softmax classifier is retrained, it convincingly beats the current state-of-the-art results on Caltech-101 and Caltech-256 datasets.

Key facts. Cited by 2,278 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Nov 2013.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 2; 2019: 2; 2020: 1; 2021: 500; 2022: 431; 2023: 440; 2024: 367; 2025: 300; 2026: 235.

2,278 papers.

Sort:

By area:

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2022Generative Adversarial Networkscited by 5,603
  3. 2021Domain Generalization: A Surveycited by 760
  4. 2022DualPrompt: Complementary Prompting for Rehearsal-free Continual Learningcited by 635
  5. 2021Perceiver IO: A General Architecture for Structured Inputs & Outputscited by 616
  6. 2021Knowledge Neurons in Pretrained Transformerscited by 590
  7. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
  8. 2022Socratic Models: Composing Zero-Shot Multimodal Reasoning with Languagecited by 513
  9. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  10. 2021Intriguing Properties of Vision Transformerscited by 446
  11. 2022MONAI: An open-source framework for deep learning in healthcarecited by 438
  12. 2024Mechanistic Interpretability for AI Safety -- A Reviewcited by 415
38 more
  1. 2021Causal Abstractions of Neural Networkscited by 401
  2. 2022DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scalecited by 400
  3. 2023SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generationcited by 376
  4. 2021Domain Adaptation for Medical Image Analysis: A Surveycited by 351
  5. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 334
  6. 2021Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformerscited by 316
  7. 2022Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learningcited by 302
  8. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 280
  9. 2021Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Predictioncited by 273
  10. 2023P+: Extended Textual Conditioning in Text-to-Image Generationcited by 242
  11. 2023Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Modelscited by 237
  12. 2024Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modificationscited by 220
  13. 2021Contrastive Learning for Compact Single Image Dehazingcited by 219
  14. 2021ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Biascited by 216
  15. 2021Trustworthy AI: From Principles to Practicescited by 206
  16. 2023Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretabilitycited by 194
  17. 2023Mitigating the Alignment Tax of RLHFcited by 181
  18. 2022CRAFT: Concept Recursive Activation FacTorization for Explainabilitycited by 177
  19. 2022Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyondcited by 171
  20. 2021No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistencycited by 165
  21. 2022Compute Trends Across Three Eras of Machine Learningcited by 161
  22. 2022The Unsurprising Effectiveness of Pre-Trained Vision Models for Controlcited by 155
  23. 2021Explainable artificial intelligence (XAI) in deep learning-based medical image analysiscited by 147
  24. 2021Student-Teacher Feature Pyramid Matching for Anomaly Detectioncited by 145
  25. 2022CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networkscited by 144
  26. 2022From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagationcited by 141
  27. 2022Natural Language Descriptions of Deep Visual Featurescited by 136
  28. 2021Fine-Grained Image Analysis with Deep Learning: A Surveycited by 135
  29. 2022Neural Prompt Searchcited by 133
  30. 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
  31. 2022Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detectioncited by 130
  32. 2022Towards Faithful Model Explanation in NLP: A Surveycited by 129
  33. 2022A Deep Learning based No-reference Quality Assessment Model for UGC Videoscited by 128
  34. 2021Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunitiescited by 125
  35. 2023Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directionscited by 123
  36. 2021TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localizationcited by 122
  37. 2022EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applicationscited by 121
  38. 2021Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypescited by 120

50 most cited of 2,278 All 2,278 (JSON)