mlsanityData to 7 Oct 2026

A Survey of Explainable AI in Deep Visual Modeling: Methods and Metrics

arXiv 2301.13445 ↗First posted 31 Jan 2023cs.CV cs.AI cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Deep visual models have widespread applications in high-stake domains. Hence, their black-box nature is currently attracting a large interest of the research community. We present the first survey in Explainable AI that focuses on the methods and metrics for interpreting deep visual models. Covering the landmark contributions along the state-of-the-art, we not only provide a taxonomic organization of the existing techniques, but also excavate a range of evaluation metrics and collate them as measures of different properties of model explanations. Along the insightful discussion on the current trends, we also discuss the challenges and future avenues for this research direction.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 55 of its 80 references that are in the map. First posted on arXiv 31 Jan 2023.

Builds on

55 of 80 references.

References · 55

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  5. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  6. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  7. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  8. 2018Sanity Checks for Saliency Mapscited by 1,149
  9. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  10. 2020Concept Bottleneck Modelscited by 1,022
  11. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  12. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 936
38 more
  1. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
  2. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  3. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 703
  4. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  5. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 467
  6. 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 416
  7. 2017Methods for Interpreting and Understanding Deep Neural Networkscited by 342
  8. 2017The (Un)reliability of saliency methodscited by 331
  9. 2016Top-down Neural Attention by Excitation Backpropcited by 318
  10. 2020Neural Additive Models: Interpretable Machine Learning with Neural Netscited by 318
  11. 2019On the (In)fidelity and Sensitivity for Explanationscited by 309
  12. 2019Understanding Deep Networks via Extremal Perturbations and Smooth Maskscited by 257
  13. 2020Concept Whitening for Interpretable Image Recognitioncited by 225
  14. 2019Full-Gradient Representation for Neural Network Visualizationcited by 189
  15. 2020Evaluating and Aggregating Feature-based Model Explanationscited by 185
  16. 2018Multimodal Explanations: Justifying Decisions and Pointing to the Evidencecited by 179
  17. 2020Compositional Explanations of Neuronscited by 172
  18. 2016Generating Visual Explanationscited by 156
  19. 2020Ground Truth Evaluation of Neural Network Explanations with CLEVR-XAIcited by 125
  20. 2021Explaining in Style: Training a GAN to explain a classifier in StyleSpacecited by 122
  21. 2019Sanity Checks for Saliency Metricscited by 119
  22. 2022A Consistent and Efficient Evaluation Strategy for Attribution Methodscited by 100
  23. 2022XAI for Transformers: Better Explanations through Conservative Propagationcited by 100
  24. 2020Neuron Shapley: Discovering the Responsible Neuronscited by 98
  25. 2019When Explanations Lie: Why Many Modified BP Attributions Failcited by 92
  26. 2021NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learningcited by 88
  27. 2022Interactive Concept Bottleneck Modelscited by 79
  28. 2020On quantitative aspects of model interpretabilitycited by 71
  29. 2019Towards Best Practice in Explaining Neural Network Decisions with LRPcited by 70
  30. 2022A Rigorous Study of Integrated Gradients Method and Extensions to Internal Neuron Attributionscited by 64
  31. 2022Framework for Evaluating Faithfulness of Local Explanationscited by 55
  32. 2022Rethinking Stability for Attribution-based Explanationscited by 52
  33. 2021A Framework for Learning Ante-hoc Explainable Models via Conceptscited by 45
  34. 2022WeightedSHAP: analyzing and improving Shapley based feature attributionscited by 36
  35. 2020Debiasing Concept-based Explanations with Causal Analysiscited by 32
  36. 2020SCOUTER: Slot Attention-based Classifier for Explainable Image Recognitioncited by 29
  37. 2021CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliencycited by 28
  38. 2022Towards Better Understanding Attribution Methodscited by 28

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 3.

4 papers.

  1. 2023Concept Distillation: Leveraging Human-Centered Explanations for Model Improvementcited by 9
  2. 2024A survey on Concept-based Approaches For Model Improvementcited by 8
  3. 2024Comprehensive Attribution: Inherently Explainable Vision Model with Feature Detectorcited by 5
  4. 2024Explainable Image Recognition via Enhanced Slot-attention Based Classifiercited by 2