mlsanityData to 7 Oct 2026

Attribution-based XAI Methods in Computer Vision: A Review

arXiv 2211.14736 ↗First posted 27 Nov 2022cs.CV cs.AIcited by 16

Not on the map. Why?

Abstract (arXiv)

The advancements in deep learning-based methods for visual perception tasks have seen astounding growth in the last decade, with widespread adoption in a plethora of application areas from autonomous driving to clinical decision support systems. Despite their impressive performance, these deep learning-based models remain fairly opaque in their decision-making process, making their deployment in human-critical tasks a risky endeavor. This in turn makes understanding the decisions made by these models crucial for their reliable deployment. Explainable AI (XAI) methods attempt to address this by offering explanations for such black-box deep learning methods. In this paper, we provide a comprehensive survey of attribution-based XAI methods in computer vision and review the existing literature for gradient-based, perturbation-based, and contrastive methods for XAI, and provide insights on the key challenges in developing and evaluating robust XAI methods.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 49 of its 73 references that are in the map. First posted on arXiv 27 Nov 2022.

Builds on

49 of 73 references.

References · 49

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  6. 2013Intriguing properties of neural networkscited by 5,114
  7. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  8. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  9. 2014Going Deeper with Convolutionscited by 4,231
  10. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  11. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  12. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
37 more
  1. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  2. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  3. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  4. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  5. 2018Sanity Checks for Saliency Mapscited by 1,149
  6. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  7. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  8. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  9. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 936
  10. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
  11. 2014Deep Learning in Neural Networks: An Overviewcited by 765
  12. 2016The Mythos of Model Interpretabilitycited by 716
  13. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 611
  14. 2013Network In Networkcited by 600
  15. 2019Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networkscited by 575
  16. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 467
  17. 2017CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learningcited by 459
  18. 2019A Survey of Deep Learning Techniques for Autonomous Drivingcited by 401
  19. 2019A large annotated medical image dataset for the development and evaluation of segmentation algorithmscited by 371
  20. 2016European Union regulations on algorithmic decision-making and a "right to explanation"cited by 343
  21. 2015Understanding Neural Networks Through Deep Visualizationcited by 332
  22. 2017The (Un)reliability of saliency methodscited by 331
  23. 2018Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negativescited by 261
  24. 2018Metrics for Explainable AI: Challenges and Prospectscited by 257
  25. 2019Understanding Deep Networks via Extremal Perturbations and Smooth Maskscited by 257
  26. 2015Explaining NonLinear Classification Decisions with Deep Taylor Decompositioncited by 248
  27. 2017Real Time Image Saliency for Black Box Classifierscited by 246
  28. 2018Techniques for Interpretable Machine Learningcited by 237
  29. 2019Explanations can be manipulated and geometry is to blamecited by 215
  30. 2017Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Modelscited by 202
  31. 2019Full-Gradient Representation for Neural Network Visualizationcited by 189
  32. 2017Visualizing Deep Neural Network Decisions: Prediction Difference Analysiscited by 166
  33. 2018Visual Interpretability for Deep Learning: a Surveycited by 155
  34. 2019XRAI: Better Attributions Through Regionscited by 116
  35. 2016Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?cited by 111
  36. 2020Explainable deep learning models in medical image analysiscited by 111
  37. 2020Contrastive Explanations in Neural Networkscited by 26

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 7; 2025: 3; 2026: 2.

16 papers.

Sort:

By area:

  1. 2023Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulationcited by 60
  2. 2024IG2: Integrated Gradient on Iterative Gradient Path for Feature Attributioncited by 12
  3. 2025Probing Deep into Temporal Profile Makes the Infrared Small Target Detector Much Bettercited by 11
  4. 2024Verifying Machine Unlearning with Explainable AIcited by 5
  5. 2024Expected Grad-CAM: Towards gradient faithfulnesscited by 4
  6. 2024Achieving Sparse Activation in Small Language Modelscited by 4
  7. 2023Fixing confirmation bias in feature attribution methods via semantic matchcited by 2
  8. 2025A Survey on Interpretability in Visual Recognitioncited by 2
  9. 2023Black-Box Anomaly Attributioncited by 1
  10. 2024Cloud-based XAI Services for Assessing Open Repository Models Under Adversarial Attackscited by 1
  11. 2024On the Black-box Explainability of Object Detection Models for Safe and Trustworthy Industrial Applicationscited by 1
  12. 2025Explainable but Vulnerable: Adversarial Attacks on XAI Explanation in Cybersecurity Applicationscited by 1
4 more
  1. 2023Counterfactual Edits for Generative Evaluationcited by 0
  2. 2024Beyond Fidelity: Explaining Vulnerability Localization of Learning-based Detectorscited by 0
  3. 2026Entropy-Centric Explainable AI for Remote Sensing Image Segmentationcited by 0
  4. 2026For Those Who Believe in Faithfulness: Optimizing the Area Under Insertion and Deletion Curves for Ranking Relative Feature Importancecited by 0