# Integrated Grad-CAM: Sensitivity-Aware Visual Explanation of Deep Convolutional Networks via Integrated Gradient-Based Scoring

arXiv: https://arxiv.org/abs/2102.07805 · HTML: https://mlsanity.com/paper/2102.07805/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 22 references that are in the map.
- First posted on arXiv 15 Feb 2021.

## Builds on (most cited first, 19 of 19)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [Top-down Neural Attention by Excitation Backprop](https://mlsanity.com/paper/1608.00507/) (2016)
- [Not Just a Black Box: Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1605.01713/) (2016)
- [Understanding Deep Networks via Extremal Perturbations and Smooth Masks](https://mlsanity.com/paper/1910.08485/) (2019)
- [Full-Gradient Representation for Neural Network Visualization](https://mlsanity.com/paper/1905.00780/) (2019)
- [Object Detectors Emerge in Deep Scene CNNs](https://mlsanity.com/paper/1412.6856/) (2014)
- [Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNs](https://mlsanity.com/paper/2008.02312/) (2020)
- [Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Models](https://mlsanity.com/paper/1908.01224/) (2019)
- [Restricting the Flow: Information Bottlenecks for Attribution](https://mlsanity.com/paper/2001.00396/) (2020)
- [Relative Attributing Propagation: Interpreting the Comparative Contributions of Individual Units in Deep Neural Networks](https://mlsanity.com/paper/1904.00605/) (2019)

## Built on by (most cited first, 16 of 16)

- [I-AI: A Controllable & Interpretable AI System for Decoding Radiologists' Intense Focus for Accurate CXR Diagnoses](https://mlsanity.com/paper/2309.13550/) (2023)
- [Learning Visual Explanations for DCNN-Based Image Classifiers Using an Attention Mechanism](https://mlsanity.com/paper/2209.11189/) (2022)
- [ProtoArgNet: Interpretable Image Classification with Super-Prototypes and Argumentation [Technical Report]](https://mlsanity.com/paper/2311.15438/) (2023)
- [Visual Explanations from Deep Networks via Riemann-Stieltjes Integrated Gradient-based Localization](https://mlsanity.com/paper/2205.10900/) (2022)
- [Expected Grad-CAM: Towards gradient faithfulness](https://mlsanity.com/paper/2406.01274/) (2024)
- [Hierarchical Symbolic Reasoning in Hyperbolic Space for Deep Discriminative Models](https://mlsanity.com/paper/2207.01916/) (2022)
- [Free Argumentative Exchanges for Explaining Image Classifiers](https://mlsanity.com/paper/2502.12995/) (2025)
- [TSGB: Target-Selective Gradient Backprop for Probing CNN Visual Saliency](https://mlsanity.com/paper/2110.05182/) (2021)
- [Overview of Class Activation Maps for Visualization Explainability](https://mlsanity.com/paper/2309.14304/) (2023)
- [Explaining Image Classification with Visual Debates](https://mlsanity.com/paper/2210.09015/) (2022)
- [CEPA: Consensus Embedded Perturbation for Agnostic Detection and Inversion of Backdoors](https://mlsanity.com/paper/2402.02034/) (2024)
- [Similarity-as-Evidence: Calibrating Overconfident VLMs for Interpretable and Label-Efficient Medical Active Learning](https://mlsanity.com/paper/2602.18867/) (2026)
- [Baseline Computation for Attribution Methods Based on Interpolated Inputs](https://mlsanity.com/paper/2204.06120/) (2022)
- [Rethinking gradient weights' influence over saliency map estimation](https://mlsanity.com/paper/2207.05374/) (2022)
- [Greedy PIG: Adaptive Integrated Gradients](https://mlsanity.com/paper/2311.06192/) (2023)
- [Class Activation Mapping in Explainable Computer Vision: A Method-Centered Review of CNN, Transformer, and Foundation-Model-Era Visual Explanations](https://mlsanity.com/paper/2608.12299/) (2026)

## Abstract (arXiv)

Visualizing the features captured by Convolutional Neural Networks (CNNs) is one of the conventional approaches to interpret the predictions made by these models in numerous image recognition applications. Grad-CAM is a popular solution that provides such a visualization by combining the activation maps obtained from the model. However, the average gradient-based terms deployed in this method underestimates the contribution of the representations discovered by the model to its predictions. Addressing this problem, we introduce a solution to tackle this issue by computing the path integral of the gradient-based terms in Grad-CAM. We conduct a thorough analysis to demonstrate the improvement achieved by our method in measuring the importance of the extracted representations for the CNN's predictions, which yields to our method's administration in object localization and model interpretation.