mlsanityData to 7 Oct 2026

Visual Explanations via Iterated Integrated Attributions

arXiv 2310.18585 ↗First posted 28 Oct 2023cs.CV cs.AIcited by 18

Not on the map. Why?

Abstract (arXiv)

We introduce Iterated Integrated Attributions (IIA) - a generic method for explaining the predictions of vision models. IIA employs iterative integration across the input image, the internal representations generated by the model, and their gradients, yielding precise and focused explanation maps. We demonstrate the effectiveness of IIA through comprehensive evaluations across various tasks, datasets, and network architectures. Our results showcase that IIA produces accurate explanation maps, outperforming other state-of-the-art explanation techniques.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 47 of its 66 references that are in the map. First posted on arXiv 28 Oct 2023.

Builds on

47 of 66 references.

References · 47

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  8. 2017Mask R-CNNcited by 7,259
  9. 2016Densely Connected Convolutional Networkscited by 6,691
  10. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  11. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  12. 2022A ConvNet for the 2020scited by 3,545
35 more
  1. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  2. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  3. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  4. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  5. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  6. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  7. 2018Sanity Checks for Saliency Mapscited by 1,149
  8. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  9. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 936
  10. 2019Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Prunedcited by 844
  11. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
  12. 2020Quantifying Attention Flow in Transformerscited by 759
  13. 2020Transformer Interpretability Beyond Attention Visualizationcited by 620
  14. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 611
  15. 2019Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networkscited by 575
  16. 2016R-FCN: Object Detection via Region-based Fully Convolutional Networkscited by 414
  17. 2021Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformerscited by 316
  18. 2016Not Just a Black Box: Learning Important Features Through Propagating Activation Differencescited by 295
  19. 2019Understanding Deep Networks via Extremal Perturbations and Smooth Maskscited by 257
  20. 2017Real Time Image Saliency for Black Box Classifierscited by 246
  21. 2016Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layerscited by 197
  22. 2019Full-Gradient Representation for Neural Network Visualizationcited by 189
  23. 2020Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNscited by 151
  24. 2019XRAI: Better Attributions Through Regionscited by 116
  25. 2017Interpreting Deep Visual Representations via Network Dissectioncited by 103
  26. 2021Guided Integrated Gradients: An Adaptive Path Method for Removing Noisecited by 102
  27. 2015Visualizing Deep Convolutional Neural Networks Using Natural Pre-Imagescited by 93
  28. 2020Attribution in Scale and Spacecited by 61
  29. 2021Towards Better Explanations of Class Activation Mappingcited by 47
  30. 2022Grad-SAM: Explaining Transformers via Gradient Self-Attention Mapscited by 42
  31. 2020Explainable Recommendations via Attentive Multi-Persona Collaborative Filteringcited by 15
  32. 2023Deep Integrated Explanationscited by 9
  33. 2021GAM: Explainable Visual Similarity and Classification via Gradient Activation Mapscited by 8
  34. 2022Interpreting BERT-based Text Similarity via Activation and Saliency Mapscited by 8
  35. 2023Learning to Explain: A Model-Agnostic Framework for Explaining Black Box Modelscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 7; 2026: 5.

18 papers.

Sort:

By area:

  1. 2024LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivitycited by 32
  2. 2024Token Transformation Matters: Towards Faithful Post-hoc Explanation for Vision Transformercited by 19
  3. 2025Where do Large Vision-Language Models Look at when Answering Questions?cited by 15
  4. 2025Dynamic Accumulated Attention Map for Interpreting Evolution of Decision-Making in Vision Transformercited by 12
  5. 2025Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformerscited by 6
  6. 2025LaSM: Layer-wise Scaling Mechanism for Defending Pop-up Attack on GUI Agentscited by 6
  7. 2025GLIMPSE: Holistic Cross-Modal Explainability for Large Vision-Language Modelscited by 5
  8. 2024T-TAME: Trainable Attention Mechanism for Explaining Convolutional Networks and Vision Transformerscited by 4
  9. 2026DAVE: Distribution-aware Attribution via ViT Gradient Decompositioncited by 3
  10. 2024AdaptGrad: Adaptive Sampling to Reduce Noisecited by 2
  11. 2025Rethinking Saliency Maps: A Cognitive Human Aligned Taxonomy and Evaluation Framework for Explanationscited by 2
  12. 2026Concept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve Robustnesscited by 2
6 more
  1. 2024REPEAT: Improving Uncertainty Estimation in Representation Learning Explainabilitycited by 1
  2. 2026DEX-AR: A Dynamic Explainability Method for Autoregressive Vision-Language Modelscited by 1
  3. 2024Axiomatization of Gradient Smoothing in Neural Networkscited by 0
  4. 2025Beyond Output Faithfulness: Learning Attributions that Preserve Computational Pathwayscited by 0
  5. 2026Attribution via Distributional Paths for Information Revelationcited by 0
  6. 2026Unraveling the Real Working Mechanism and Inherent Flaws of GAE: A Method for Interpreting Transformer Processes from an Economic Perspectivecited by 0