mlsanityData to 14 Oct 2026

SmoothGrad: removing noise by adding noise

arXiv 1706.03825 ↗First posted 12 Jun 2017cs.LG cs.CV stat.MLcited by 1,109

Not on the map. Why?

Cited by 22 in Mechanistic interpretability, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Explaining the output of a deep network remains a challenge. In the case of an image classifier, one type of explanation is to identify pixels that strongly influence the final decision. A starting point for this strategy is the gradient of the class score function with respect to the input image. This gradient can be interpreted as a sensitivity map, and there are several techniques that elaborate on this basic idea. This paper makes two contributions: it introduces SmoothGrad, a simple method that can help visually sharpen gradient-based sensitivity maps, and it discusses lessons in the visualization of these maps. We publish the code for our experiments and a website with our results.

Key facts. Cited by 1,109 papers in the map (data through 14 Oct 2026). First posted on arXiv 12 Jun 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 0; 2021: 192; 2022: 211; 2023: 219; 2024: 212; 2025: 141; 2026: 133.

1,109 papers.

Sort:

By area:

  1. 2022MONAI: An open-source framework for deep learning in healthcarecited by 448
  2. 2022Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskcited by 431
  3. 2024Mechanistic Interpretability for AI Safety -- A Reviewcited by 422
  4. 2023SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generationcited by 386
  5. 2021Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformerscited by 320
  6. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 281
  7. 2022CRAFT: Concept Recursive Activation FacTorization for Explainabilitycited by 178
  8. 2022The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspectivecited by 159
  9. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  10. 2021Deep Stable Learning for Out-Of-Distribution Generalizationcited by 153
  11. 2022From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagationcited by 141
  12. 2021Benchmarking and Survey of Explanation Methods for Black Box Modelscited by 136
38 more
  1. 2022Towards Faithful Model Explanation in NLP: A Surveycited by 130
  2. 2021IA-RED2: Interpretability-Aware Redundancy Reduction for Vision Transformerscited by 127
  3. 2022OpenXAI: Towards a Transparent Evaluation of Model Explanationscited by 126
  4. 2021FastSHAP: Real-Time Shapley Value Estimationcited by 125
  5. 2021Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypescited by 120
  6. 2024AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformerscited by 120
  7. 2021Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyondcited by 118
  8. 2021Do Concept Bottleneck Models Learn as Intended?cited by 116
  9. 2021Salient ImageNet: How to discover spurious features in Deep Learning?cited by 114
  10. 2023A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimationcited by 109
  11. 2021BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentationcited by 105
  12. 2021Guided Integrated Gradients: An Adaptive Path Method for Removing Noisecited by 102
  13. 2022A Consistent and Efficient Evaluation Strategy for Attribution Methodscited by 102
  14. 2021Do Feature Attribution Methods Correctly Attribute Features?cited by 98
  15. 2021What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methodscited by 98
  16. 2024ContextCite: Attributing Model Generation to Contextcited by 98
  17. 2022Improving Adversarial Transferability via Neuron Attribution-Based Attackscited by 93
  18. 2021A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Conceptscited by 91
  19. 2023Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanationscited by 90
  20. 2024What makes unlearning hard and what to do about itcited by 89
  21. 2021The effectiveness of feature attribution methods and its correlation with automatic evaluation scorescited by 88
  22. 2021The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanationscited by 87
  23. 2022Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanationscited by 85
  24. 2024A Primer on the Inner Workings of Transformer-based Language Modelscited by 85
  25. 2021Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methodscited by 83
  26. 2021Leveraging Sparse Linear Layers for Debuggable Deep Networkscited by 82
  27. 2021Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Bettercited by 79
  28. 2022Impossibility Theorems for Feature Attributioncited by 78
  29. 2022Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanationscited by 77
  30. 2022What do Vision Transformers Learn? A Visual Explorationcited by 76
  31. 2021XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanationscited by 73
  32. 2025Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Modelscited by 73
  33. 2021Improving Deep Learning Interpretability by Saliency Guided Trainingcited by 68
  34. 2021Deep One-Class Classification via Interpolated Gaussian Descriptorcited by 67
  35. 2024SelfIE: Self-Interpretation of Large Language Model Embeddingscited by 67
  36. 2024Uncovering Safety Risks of Large Language Models through Concept Activation Vectorcited by 67
  37. 2021High Fidelity Visualization of What Your Self-Supervised Representation Knows Aboutcited by 66
  38. 2022TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversationscited by 66

50 most cited of 1,109 All 1,109 (JSON)