mlsanityData to 14 Oct 2026

Deep Integrated Explanations

arXiv 2310.15368 ↗First posted 23 Oct 2023cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

This paper presents Deep Integrated Explanations (DIX) - a universal method for explaining vision models. DIX generates explanation maps by integrating information from the intermediate representations of the model, coupled with their corresponding gradients. Through an extensive array of both objective and subjective evaluations spanning diverse tasks, datasets, and model configurations, we showcase the efficacy of DIX in generating faithful and accurate explanation maps, while surpassing current state-of-the-art methods.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 59 of its 91 references that are in the map. First posted on arXiv 23 Oct 2023.

Builds on

59 of 91 references.

References · 59

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  6. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  7. 2020End-to-End Object Detection with Transformerscited by 7,414
  8. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  9. 2017Mask R-CNNcited by 7,277
  10. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  11. 2016Densely Connected Convolutional Networkscited by 6,720
  12. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
38 more
  1. 2022A ConvNet for the 2020scited by 3,579
  2. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  3. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  4. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  5. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  6. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,222
  7. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,487
  8. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  9. 2018Sanity Checks for Saliency Mapscited by 1,156
  10. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,139
  11. 2017Neural Collaborative Filteringcited by 1,111
  12. 2017SmoothGrad: removing noise by adding noisecited by 1,109
  13. 2014Striving for Simplicity: The All Convolutional Netcited by 990
  14. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 939
  15. 2019Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Prunedcited by 856
  16. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 838
  17. 2020Quantifying Attention Flow in Transformerscited by 775
  18. 2019Neural Graph Collaborative Filteringcited by 661
  19. 2020Transformer Interpretability Beyond Attention Visualizationcited by 627
  20. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 612
  21. 2019Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networkscited by 582
  22. 2021Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformerscited by 320
  23. 2016Not Just a Black Box: Learning Important Features Through Propagating Activation Differencescited by 297
  24. 2019Understanding Deep Networks via Extremal Perturbations and Smooth Maskscited by 259
  25. 2017Real Time Image Saliency for Black Box Classifierscited by 246
  26. 2019Full-Gradient Representation for Neural Network Visualizationcited by 191
  27. 2020Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNscited by 151
  28. 2019GANSynth: Adversarial Neural Audio Synthesiscited by 116
  29. 2019XRAI: Better Attributions Through Regionscited by 116
  30. 2017Interpreting Deep Visual Representations via Network Dissectioncited by 103
  31. 2021Guided Integrated Gradients: An Adaptive Path Method for Removing Noisecited by 102
  32. 2015Visualizing Deep Convolutional Neural Networks Using Natural Pre-Imagescited by 93
  33. 2016Item2Vec: Neural Item Embedding for Collaborative Filteringcited by 72
  34. 2020Attribution in Scale and Spacecited by 61
  35. 2021Towards Better Explanations of Class Activation Mappingcited by 47
  36. 2022Grad-SAM: Explaining Transformers via Gradient Self-Attention Mapscited by 42
  37. 2018SING: Symbol-to-Instrument Neural Generatorcited by 23
  38. 2020Explainable Recommendations via Attentive Multi-Persona Collaborative Filteringcited by 16

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 1; 2025: 0; 2026: 7.

10 papers.

  1. 2023Visual Explanations via Iterated Integrated Attributionscited by 19
  2. 2024Token Transformation Matters: Towards Faithful Post-hoc Explanation for Vision Transformercited by 19
  3. 2023Learning to Explain: A Model-Agnostic Framework for Explaining Black Box Modelscited by 4
  4. 2026Concept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve Robustnesscited by 2
  5. 2026Debunking Grad-ECLIP: A Comprehensive Study on Its Incorrectness and Fundamental Principles for Model Interpretationcited by 2
  6. 2026Transformer Interpretability from Perspective of Attention and Gradientcited by 0
  7. 2026The Neglected Baseline in Model Interpretationcited by 0
  8. 2026Generic Interpretation Approach for Transformer Models Incorporating Heterogenous Attention Structurescited by 0
  9. 2026Unraveling the Real Working Mechanism and Inherent Flaws of GAE: A Method for Interpreting Transformer Processes from an Economic Perspectivecited by 0
  10. 2026ConEx: Human-Interpretable Saliency Maps via Concept-Aware Attributioncited by 0