mlsanityData to 7 Oct 2026

Visualizing Deep Neural Network Decisions: Prediction Difference Analysis

arXiv 1702.04595 ↗First posted 15 Feb 2017cs.CV cs.AIcited by 166

Not on the map. Why?

Abstract (arXiv)

This article presents the prediction difference analysis method for visualizing the response of a deep neural network to a specific input. When classifying images, the method highlights areas in a given input image that provide evidence for or against a certain class. It overcomes several shortcoming of previous methods and provides great additional insight into the decision making process of classifiers. Making neural network decisions interpretable through visualization is important both to improve models and to accelerate the adoption of black-box classifiers in application areas such as medicine. We illustrate the method in experiments on natural images (ImageNet data), as well as medical images (MRI brain scans).

Key facts. Cited by 166 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Feb 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 44; 2022: 42; 2023: 28; 2024: 33; 2025: 13; 2026: 6.

166 papers.

Sort:

By area:

  1. 2021Explainable artificial intelligence (XAI) in deep learning-based medical image analysiscited by 147
  2. 2021The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanationscited by 86
  3. 2022Distilling Model Failures as Directions in Latent Spacecited by 82
  4. 2021Neuron-level Interpretation of Deep NLP Models: A Surveycited by 81
  5. 2021Contrastive Explanations for Model Interpretabilitycited by 75
  6. 2021Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretationscited by 59
  7. 2022Visual Recognition with Deep Nearest Centroidscited by 59
  8. 2024Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Surveycited by 52
  9. 2023FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methodscited by 49
  10. 2022Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvementcited by 48
  11. 2022Rethinking Attention-Model Explainability through Faithfulness Violation Testcited by 43
  12. 2021Automatic Sleep Staging of EEG Signals: Recent Development, Challenges, and Future Directionscited by 41
38 more
  1. 2022Model Zoos: A Dataset of Diverse Populations of Neural Network Modelscited by 38
  2. 2022Missingness Bias in Model Debuggingcited by 36
  3. 2022WeightedSHAP: analyzing and improving Shapley based feature attributionscited by 36
  4. 2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
  5. 2021Fast Axiomatic Attribution for Neural Networkscited by 35
  6. 2025Visual Large Language Models for Generalized and Specialized Applicationscited by 35
  7. 2022Guidelines and Evaluation of Clinical Explainable AI in Medical Image Analysiscited by 34
  8. 2025A Survey on Mechanistic Interpretability for Multi-Modal Foundation Modelscited by 34
  9. 2021Neural Response Interpretation through the Lens of Critical Pathwayscited by 32
  10. 2024Facing the Elephant in the Room: Visual Prompt Tuning or Full Finetuning?cited by 31
  11. 2024MambaLRP: Explaining Selective State Space Sequence Modelscited by 31
  12. 2022Making Heads or Tails: Towards Semantically Consistent Visual Counterfactualscited by 30
  13. 2023Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectivescited by 30
  14. 2022Diffeomorphic Counterfactuals with Generative Modelscited by 29
  15. 2021CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliencycited by 28
  16. 2024Decoupling Pixel Flipping and Occlusion Strategy for Consistent XAI Benchmarkscited by 28
  17. 2021Refining Language Models with Compositional Explanationscited by 27
  18. 2021ECINN: Efficient Counterfactuals from Invertible Neural Networkscited by 26
  19. 2021Visual Explanations from Spiking Neural Networks using Interspike Intervalscited by 26
  20. 2024Mechanistic?cited by 25
  21. 2021Counterfactual Explanations for Models of Codecited by 24
  22. 2022Human-Centered Concept Explanations for Neural Networkscited by 23
  23. 2022Robust Explanation Constraints for Neural Networkscited by 23
  24. 2021Levels of explainable artificial intelligence for human-aligned conversational explanationscited by 21
  25. 2024Optimal ablation for interpretabilitycited by 21
  26. 2022Concept Gradient: Concept-based Interpretation Without Linear Assumptioncited by 20
  27. 2022Evaluating Explainable AI on a Multi-Modal Medical Imaging Task: Can Existing Algorithms Fulfill Clinical Requirements?cited by 19
  28. 2023SpArX: Sparse Argumentative Explanations for Neural Networks [Technical Report]cited by 18
  29. 2024Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Modelscited by 17
  30. 2021PredDiff: Explanations and Interactions from Conditional Expectationscited by 16
  31. 2022Attribution-based XAI Methods in Computer Vision: A Reviewcited by 16
  32. 2023IDGI: A Framework to Eliminate Explanation Noise from Integrated Gradientscited by 16
  33. 2023HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagationcited by 16
  34. 2021Keep CALM and Improve Visual Feature Attributioncited by 15
  35. 2021Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution Viewcited by 15
  36. 2021A Survey on Understanding, Visualizations, and Explanation of Deep Neural Networkscited by 14
  37. 2023Illuminati: Towards Explaining Graph Neural Networks for Cybersecurity Analysiscited by 14
  38. 2021Explainability Is in the Mind of the Beholder: Establishing the Foundations of Explainable Artificial Intelligencecited by 13

50 most cited of 166 All 166 (JSON)