mlsanityData to 14 Oct 2026

Grad-CAM: Why did you say that?

arXiv 1611.07450 ↗First posted 22 Nov 2016stat.ML cs.CV cs.LGcited by 161

Not on the map. Why?

Abstract (arXiv)

We propose a technique for making Convolutional Neural Network (CNN)-based models more transparent by visualizing input regions that are 'important' for predictions -- or visual explanations. Our approach, called Gradient-weighted Class Activation Mapping (Grad-CAM), uses class-specific gradient information to localize important regions. These localizations are combined with existing pixel-space visualizations to create a novel high-resolution and class-discriminative visualization called Guided Grad-CAM. These methods help better understand CNN-based models, including image captioning and visual question answering (VQA) models. We evaluate our visual explanations by measuring their ability to discriminate between classes, to inspire trust in humans, and their correlation with occlusion maps. Grad-CAM provides a new way to understand CNN-based models. We have released code, an online demo hosted on CloudCV, and a full version of this extended abstract.

Key facts. Cited by 161 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 Nov 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 18; 2022: 22; 2023: 43; 2024: 37; 2025: 25; 2026: 16.

161 papers.

Sort:

By area:

  1. 2023Learning Concise and Descriptive Attributes for Visual Recognitioncited by 73
  2. 2021High Fidelity Visualization of What Your Self-Supervised Representation Knows Aboutcited by 66
  3. 2022Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Offcited by 61
  4. 2023From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuningcited by 56
  5. 2021A Review on Explainability in Multimodal Deep Neural Netscited by 46
  6. 2024Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Eracited by 46
  7. 2022Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Biascited by 43
  8. 2022Are Vision Transformers Robust to Spurious Correlations?cited by 36
  9. 2023Spurious Feature Diversification Improves Out-of-distribution Generalizationcited by 26
  10. 2023Multimodal Explainable Artificial Intelligence: A Comprehensive Review of Methodological Advances and Future Research Directionscited by 25
  11. 2022Are Deep Neural Networks SMARTer than Second Graders?cited by 24
  12. 2024How Far are AI-generated Videos from Simulating the 3D Visual World: A Learned 3D Evaluation Approachcited by 16
38 more
  1. 2022On the Relationship Between Explanation and Prediction: A Causal Viewcited by 14
  2. 2021CAM-loss: Towards Learning Spatially Discriminative Feature Representationscited by 13
  3. 2022Correct-by-Construction Runtime Enforcement in AI -- A Surveycited by 12
  4. 2023Explainability of Vision Transformers: A Comprehensive Review and New Perspectivescited by 12
  5. 2023Towards Visual Saliency Explanations of Face Verificationcited by 11
  6. 2024Explainable Attribute-Based Speaker Verificationcited by 11
  7. 2024MA-AVT: Modality Alignment for Parameter-Efficient Audio-Visual Transformerscited by 11
  8. 2021SelectAugment: Hierarchical Deterministic Sample Selection for Data Augmentationcited by 10
  9. 2022New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Soundcited by 10
  10. 2023Can We Trust Explainable AI Methods on ASR? An Evaluation on Phoneme Recognitioncited by 10
  11. 2021SCALP -- Supervised Contrastive Learning for Cardiopulmonary Disease Classification and Localization in Chest X-rays using Patient Metadatacited by 9
  12. 2022Generalizing Adversarial Explanations with Grad-CAMcited by 9
  13. 2021Cause and Effect: Hierarchical Concept-based Explanation of Neural Networkscited by 8
  14. 2021GETAM: Gradient-weighted Element-wise Transformer Attention Map for Weakly-supervised Semantic segmentationcited by 8
  15. 2023Sanity checks for patch visualisation in prototype-based image classificationcited by 8
  16. 2024DAWN: Domain-Adaptive Weakly Supervised Nuclei Segmentation via Cross-Task Interactionscited by 8
  17. 2024KAN You See It? KANs and Sentinel for Effective and Explainable Crop Field Segmentationcited by 8
  18. 2025MIRAGE: Towards AI-Generated Image Detection in the Wildcited by 8
  19. 2022Radiomics-Guided Global-Local Transformer for Weakly Supervised Pathology Localization in Chest X-Rayscited by 7
  20. 2022DASH: Visual Analytics for Debiasing Image Classification via User-Driven Synthetic Data Augmentationcited by 7
  21. 2022Zero-shot Active Visual Search (ZAVIS): Intelligent Object Search for Robotic Assistantscited by 7
  22. 2023Dataset Bias Mitigation in Multiple-Choice Visual Question Answering and Beyondcited by 7
  23. 2026Do Medical Vision Language Models Actually See? A Counterfactual Grounding Framework and Hard-Negative Contrastive Training for Visually-Reliant Medical VLMscited by 7
  24. 2021Knowledge-Augmented Contrastive Learning for Abnormality Classification and Localization in Chest X-rays with Radiomics using a Feedback Loopcited by 6
  25. 2021Knee Osteoarthritis Severity Prediction using an Attentive Multi-Scale Deep Convolutional Neural Networkcited by 6
  26. 2021Soundify: Matching Sound Effects to Videocited by 6
  27. 2023Revisiting Image Classifier Training for Improved Certified Robust Defense against Adversarial Patchescited by 6
  28. 2024From Movements to Metrics: Evaluating Explainable AI Methods in Skeleton-Based Human Activity Recognitioncited by 6
  29. 2024On the Value of Labeled Data and Symbolic Methods for Hidden Neuron Activation Analysiscited by 6
  30. 2024Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion Modelcited by 6
  31. 2021Improving Attribution Methods by Learning Submodular Functionscited by 5
  32. 2021Explainable Deep Reinforcement Learning for Portfolio Management: An Empirical Approachcited by 5
  33. 2023Fairness in AI Systems: Mitigating gender bias from language-vision modelscited by 5
  34. 2023A Strong and Simple Deep Learning Baseline for BCI MI Decodingcited by 5
  35. 2025ConceptScope: Characterizing Dataset Bias via Disentangled Visual Conceptscited by 5
  36. 2022Multi-task UNet: Jointly Boosting Saliency Prediction and Disease Classification on Chest X-ray Imagescited by 4
  37. 2022CtrlFormer: Learning Transferable State Representation for Visual Control via Transformercited by 4
  38. 2022Concept-Based Explanations for Tabular Datacited by 4

50 most cited of 161 All 161 (JSON)