# Use HiResCAM instead of Grad-CAM for faithful explanations of convolutional neural networks

arXiv: https://arxiv.org/abs/2011.08891 · HTML: https://mlsanity.com/paper/2011.08891/

## Key facts

- Cited by 79 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Nov 2020.

## Built on by (most cited first, 30 of 79)

- [Common Sense Reasoning for Deepfake Detection](https://mlsanity.com/paper/2402.00126/) (2024)
- [Neural Networks are Decision Trees](https://mlsanity.com/paper/2210.05189/) (2022)
- [LangXAI: Integrating Large Vision Models for Generating Textual Explanations to Enhance Explainability in Visual Perception Tasks](https://mlsanity.com/paper/2402.12525/) (2024)
- [Learning Pairwise Interaction for Generalizable DeepFake Detection](https://mlsanity.com/paper/2302.13288/) (2023)
- [DiG-IN: Diffusion Guidance for Investigating Networks -- Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations](https://mlsanity.com/paper/2311.17833/) (2023)
- [Explainable AI (XAI) in Image Segmentation in Medicine, Industry, and Beyond: A Survey](https://mlsanity.com/paper/2405.01636/) (2024)
- [A Framework for Interpretability in Machine Learning for Medical Imaging](https://mlsanity.com/paper/2310.01685/) (2023)
- [Benchmarking XAI Explanations with Human-Aligned Evaluations](https://mlsanity.com/paper/2411.02470/) (2024)
- [Visualizing and Understanding Contrastive Learning](https://mlsanity.com/paper/2206.09753/) (2022)
- [Enhancing Concept Localization in CLIP-based Concept Bottleneck Models](https://mlsanity.com/paper/2510.07115/) (2025)
- [Explaining the Implicit Neural Canvas: Connecting Pixels to Neurons by Tracing their Contributions](https://mlsanity.com/paper/2401.10217/) (2024)
- [Vision Transformers with Natural Language Semantics](https://mlsanity.com/paper/2402.17863/) (2024)
- [LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributions](https://mlsanity.com/paper/2411.16760/) (2024)
- [CAMs as Shapley Value-based Explainers](https://mlsanity.com/paper/2501.06261/) (2025)
- [Identifying Drivers of Predictive Aleatoric Uncertainty](https://mlsanity.com/paper/2312.07252/) (2023)
- [Transcending Adversarial Perturbations: Manifold-Aided Adversarial Examples with Legitimate Semantics](https://mlsanity.com/paper/2402.03095/) (2024)
- [CAM-Based Methods Can See through Walls](https://mlsanity.com/paper/2404.01964/) (2024)
- [Expected Grad-CAM: Towards gradient faithfulness](https://mlsanity.com/paper/2406.01274/) (2024)
- [Zero-shot Translation of Attention Patterns in VQA Models to Natural Language](https://mlsanity.com/paper/2311.05043/) (2023)
- [Pairwise Matching of Intermediate Representations for Fine-grained Explainability](https://mlsanity.com/paper/2503.22881/) (2025)
- [A Simple Detector with Frame Dynamics is a Strong Tracker](https://mlsanity.com/paper/2505.04917/) (2025)
- [Quantitative Analysis of Primary Attribution Explainable Artificial Intelligence Methods for Remote Sensing Image Classification](https://mlsanity.com/paper/2306.04037/) (2023)
- [Leveraging CAM Algorithms for Explaining Medical Semantic Segmentation](https://mlsanity.com/paper/2409.20287/) (2024)
- [FaceX: Understanding Face Attribute Classifiers through Summary Model Explanations](https://mlsanity.com/paper/2412.07313/) (2024)
- [Large-scale School Mapping using Weakly Supervised Deep Learning for Universal School Connectivity](https://mlsanity.com/paper/2412.14870/) (2024)
- [A Survey on Interpretability in Visual Recognition](https://mlsanity.com/paper/2507.11099/) (2025)
- [Benchmarking Class Activation Map Methods for Explainable Brain Hemorrhage Classification on Hemorica Dataset](https://mlsanity.com/paper/2508.17699/) (2025)
- [Explainable multiple abnormality classification of chest CT volumes](https://mlsanity.com/paper/2111.12215/) (2021)
- [Towards an Error-free Deep Occupancy Detector for Smart Camera Parking System](https://mlsanity.com/paper/2208.08220/) (2022)
- [MetaCAM: Ensemble-Based Class Activation Map](https://mlsanity.com/paper/2307.16863/) (2023)

## Abstract (arXiv)

Explanation methods facilitate the development of models that learn meaningful concepts and avoid exploiting spurious correlations. We illustrate a previously unrecognized limitation of the popular neural network explanation method Grad-CAM: as a side effect of the gradient averaging step, Grad-CAM sometimes highlights locations the model did not actually use. To solve this problem, we propose HiResCAM, a novel class-specific explanation method that is guaranteed to highlight only the locations the model used to make each prediction. We prove that HiResCAM is a generalization of CAM and explore the relationships between HiResCAM and other gradient-based explanation methods. Experiments on PASCAL VOC 2012, including crowd-sourced evaluations, illustrate that while HiResCAM's explanations faithfully reflect the model, Grad-CAM often expands the attention to create bigger and smoother visualizations. Overall, this work advances convolutional neural network explanation approaches and may aid in the development of trustworthy models for sensitive applications.