# Grad-CAM: Why did you say that?

arXiv: https://arxiv.org/abs/1611.07450 · HTML: https://mlsanity.com/paper/1611.07450/

## Key facts

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

## Built on by (most cited first, 30 of 161)

- [Learning Concise and Descriptive Attributes for Visual Recognition](https://mlsanity.com/paper/2308.03685/) (2023)
- [High Fidelity Visualization of What Your Self-Supervised Representation Knows About](https://mlsanity.com/paper/2112.09164/) (2021)
- [Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off](https://mlsanity.com/paper/2209.09056/) (2022)
- [From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning](https://mlsanity.com/paper/2310.00492/) (2023)
- [A Review on Explainability in Multimodal Deep Neural Nets](https://mlsanity.com/paper/2105.07878/) (2021)
- [Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era](https://mlsanity.com/paper/2403.08946/) (2024)
- [Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias](https://mlsanity.com/paper/2212.11261/) (2022)
- [Are Vision Transformers Robust to Spurious Correlations?](https://mlsanity.com/paper/2203.09125/) (2022)
- [Spurious Feature Diversification Improves Out-of-distribution Generalization](https://mlsanity.com/paper/2309.17230/) (2023)
- [Multimodal Explainable Artificial Intelligence: A Comprehensive Review of Methodological Advances and Future Research Directions](https://mlsanity.com/paper/2306.05731/) (2023)
- [Are Deep Neural Networks SMARTer than Second Graders?](https://mlsanity.com/paper/2212.09993/) (2022)
- [How Far are AI-generated Videos from Simulating the 3D Visual World: A Learned 3D Evaluation Approach](https://mlsanity.com/paper/2406.19568/) (2024)
- [On the Relationship Between Explanation and Prediction: A Causal View](https://mlsanity.com/paper/2212.06925/) (2022)
- [CAM-loss: Towards Learning Spatially Discriminative Feature Representations](https://mlsanity.com/paper/2109.01359/) (2021)
- [Correct-by-Construction Runtime Enforcement in AI -- A Survey](https://mlsanity.com/paper/2208.14426/) (2022)
- [Explainability of Vision Transformers: A Comprehensive Review and New Perspectives](https://mlsanity.com/paper/2311.06786/) (2023)
- [Towards Visual Saliency Explanations of Face Verification](https://mlsanity.com/paper/2305.08546/) (2023)
- [Explainable Attribute-Based Speaker Verification](https://mlsanity.com/paper/2405.19796/) (2024)
- [MA-AVT: Modality Alignment for Parameter-Efficient Audio-Visual Transformers](https://mlsanity.com/paper/2406.04930/) (2024)
- [SelectAugment: Hierarchical Deterministic Sample Selection for Data Augmentation](https://mlsanity.com/paper/2112.02862/) (2021)
- [New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound](https://mlsanity.com/paper/2211.02912/) (2022)
- [Can We Trust Explainable AI Methods on ASR? An Evaluation on Phoneme Recognition](https://mlsanity.com/paper/2305.18011/) (2023)
- [SCALP -- Supervised Contrastive Learning for Cardiopulmonary Disease Classification and Localization in Chest X-rays using Patient Metadata](https://mlsanity.com/paper/2110.14787/) (2021)
- [Generalizing Adversarial Explanations with Grad-CAM](https://mlsanity.com/paper/2204.05427/) (2022)
- [Cause and Effect: Hierarchical Concept-based Explanation of Neural Networks](https://mlsanity.com/paper/2105.07033/) (2021)
- [GETAM: Gradient-weighted Element-wise Transformer Attention Map for Weakly-supervised Semantic segmentation](https://mlsanity.com/paper/2112.02841/) (2021)
- [Sanity checks for patch visualisation in prototype-based image classification](https://mlsanity.com/paper/2311.16120/) (2023)
- [DAWN: Domain-Adaptive Weakly Supervised Nuclei Segmentation via Cross-Task Interactions](https://mlsanity.com/paper/2404.14956/) (2024)
- [KAN You See It? KANs and Sentinel for Effective and Explainable Crop Field Segmentation](https://mlsanity.com/paper/2408.07040/) (2024)
- [MIRAGE: Towards AI-Generated Image Detection in the Wild](https://mlsanity.com/paper/2508.13223/) (2025)

## 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.