mlsanityData to 7 Oct 2026

Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks

arXiv 1710.11063 ↗First posted 30 Oct 2017cs.CVcited by 936

Not on the map. Why?

Cited by 22 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Over the last decade, Convolutional Neural Network (CNN) models have been highly successful in solving complex vision problems. However, these deep models are perceived as "black box" methods considering the lack of understanding of their internal functioning. There has been a significant recent interest in developing explainable deep learning models, and this paper is an effort in this direction. Building on a recently proposed method called Grad-CAM, we propose a generalized method called Grad-CAM++ that can provide better visual explanations of CNN model predictions, in terms of better object localization as well as explaining occurrences of multiple object instances in a single image, when compared to state-of-the-art. We provide a mathematical derivation for the proposed method, which uses a weighted combination of the positive partial derivatives of the last convolutional layer feature maps with respect to a specific class score as weights to generate a visual explanation for the corresponding class label. Our extensive experiments and evaluations, both subjective and objective, on standard datasets showed that Grad-CAM++ provides promising human-interpretable visual explanations for a given CNN architecture across multiple tasks including classification, image caption generation and 3D action recognition; as well as in new settings such as knowledge distillation.

Key facts. Cited by 936 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Oct 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 139; 2022: 146; 2023: 160; 2024: 207; 2025: 152; 2026: 132.

936 papers.

Sort:

By area:

  1. 2021Deep Neural Networks and Tabular Data: A Surveycited by 489
  2. 2023SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generationcited by 376
  3. 2022Detecting Deepfakes with Self-Blended Imagescited by 332
  4. 2023On Evaluating Adversarial Robustness of Large Vision-Language Modelscited by 281
  5. 2021Simultaneously Localize, Segment and Rank the Camouflaged Objectscited by 198
  6. 2022Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cutcited by 166
  7. 2021Benchmarking and Survey of Explanation Methods for Black Box Modelscited by 136
  8. 2021Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical Worldcited by 127
  9. 2023Aligning Bag of Regions for Open-Vocabulary Object Detectioncited by 119
  10. 2021Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyondcited by 116
  11. 2021Representative Forgery Mining for Fake Face Detectioncited by 108
  12. 2022An Empirical Study of Remote Sensing Pretrainingcited by 105
38 more
  1. 2021What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methodscited by 98
  2. 2021Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understandingcited by 97
  3. 2023A Closer Look at the Explainability of Contrastive Language-Image Pre-trainingcited by 95
  4. 2021The effectiveness of feature attribution methods and its correlation with automatic evaluation scorescited by 87
  5. 2021CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithmscited by 85
  6. 2021Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methodscited by 83
  7. 2022Learning Affordance Grounding from Exocentric Imagescited by 82
  8. 2021Explanations in Autonomous Driving: A Surveycited by 80
  9. 2022Diffusion Models for Counterfactual Explanationscited by 79
  10. 2022Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanationscited by 77
  11. 2025Harmonizing Visual Representations for Unified Multimodal Understanding and Generationcited by 74
  12. 2021Explainable Artificial Intelligence for Autonomous Driving: A Comprehensive Overview and Field Guide for Future Research Directionscited by 73
  13. 2021IAIA-BL: A Case-based Interpretable Deep Learning Model for Classification of Mass Lesions in Digital Mammographycited by 72
  14. 2021Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Futurecited by 67
  15. 2023LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Groundingcited by 64
  16. 2022Transformers in Remote Sensing: A Surveycited by 61
  17. 2023Class Attention Transfer Based Knowledge Distillationcited by 61
  18. 2021Synthetic Benchmarks for Scientific Research in Explainable Machine Learningcited by 59
  19. 2021Large-Scale Unsupervised Object Discoverycited by 54
  20. 2021Meaningfully Debugging Model Mistakes using Conceptual Counterfactual Explanationscited by 53
  21. 2023Online Prototype Learning for Online Continual Learningcited by 53
  22. 2023Learning Bottleneck Concepts in Image Classificationcited by 49
  23. 2021Exploiting Explanations for Model Inversion Attackscited by 48
  24. 2021Towards Better Explanations of Class Activation Mappingcited by 47
  25. 2023Adversarial Counterfactual Visual Explanationscited by 47
  26. 2023Domain Generalization for Medical Image Analysis: A Reviewcited by 47
  27. 2022A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Predictioncited by 46
  28. 2022Overlooked factors in concept-based explanations: Dataset choice, concept learnability, and human capabilitycited by 46
  29. 2024Incremental Residual Concept Bottleneck Modelscited by 43
  30. 2021A Survey on Graph-Based Deep Learning for Computational Histopathologycited by 41
  31. 2021An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defencescited by 41
  32. 2022Metrics for saliency map evaluation of deep learning explanation methodscited by 40
  33. 2021Harnessing Perceptual Adversarial Patches for Crowd Countingcited by 39
  34. 2022Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysiscited by 38
  35. 2023Shape-Erased Feature Learning for Visible-Infrared Person Re-Identificationcited by 38
  36. 2021Group-CAM: Group Score-Weighted Visual Explanations for Deep Convolutional Networkscited by 36
  37. 2024Efficient Generation of Targeted and Transferable Adversarial Examples for Vision-Language Models Via Diffusion Modelscited by 36
  38. 2021One-Class Classification: A Surveycited by 35

50 most cited of 936 All 936 (JSON)