# IDGI: A Framework to Eliminate Explanation Noise from Integrated Gradients

arXiv: https://arxiv.org/abs/2303.14242 · HTML: https://mlsanity.com/paper/2303.14242/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 52 references that are in the map.
- First posted on arXiv 24 Mar 2023.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Multi-View 3D Object Detection Network for Autonomous Driving](https://mlsanity.com/paper/1611.07759/) (2016)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [Interpretation of Neural Networks is Fragile](https://mlsanity.com/paper/1710.10547/) (2017)
- [The many Shapley values for model explanation](https://mlsanity.com/paper/1908.08474/) (2019)
- [Real Time Image Saliency for Black Box Classifiers](https://mlsanity.com/paper/1705.07857/) (2017)
- [DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving](https://mlsanity.com/paper/1505.00256/) (2015)
- [Visualizing Deep Neural Network Decisions: Prediction Difference Analysis](https://mlsanity.com/paper/1702.04595/) (2017)
- [FastSHAP: Real-Time Shapley Value Estimation](https://mlsanity.com/paper/2107.07436/) (2021)
- [XRAI: Better Attributions Through Regions](https://mlsanity.com/paper/1906.02825/) (2019)
- [Guided Integrated Gradients: An Adaptive Path Method for Removing Noise](https://mlsanity.com/paper/2106.09788/) (2021)
- [Attribution in Scale and Space](https://mlsanity.com/paper/2004.03383/) (2020)

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

- [Manifold Integrated Gradients: Riemannian Geometry for Feature Attribution](https://mlsanity.com/paper/2405.09800/) (2024)
- [Post-hoc Part-prototype Networks](https://mlsanity.com/paper/2406.03421/) (2024)
- [Tokenize Image Patches: Global Context Fusion for Effective Haze Removal in Large Images](https://mlsanity.com/paper/2504.09621/) (2025)
- [Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanation](https://mlsanity.com/paper/2402.08845/) (2024)
- [LICO: Explainable Models with Language-Image Consistency](https://mlsanity.com/paper/2310.09821/) (2023)
- [Supervised Fine-Tuning Achieve Rapid Task Adaption Via Alternating Attention Head Activation Patterns](https://mlsanity.com/paper/2409.15820/) (2024)
- [QUCE: The Minimisation and Quantification of Path-Based Uncertainty for Generative Counterfactual Explanations](https://mlsanity.com/paper/2402.17516/) (2024)
- [AdaptGrad: Adaptive Sampling to Reduce Noise](https://mlsanity.com/paper/2410.07711/) (2024)
- [Time series saliency maps: explaining models across multiple domains](https://mlsanity.com/paper/2505.13100/) (2025)
- [Enhancing Interpretability for Vision Models via Shapley Value Optimization](https://mlsanity.com/paper/2512.14354/) (2025)
- [SAfER: Layer-Level Sensitivity Assessment for Efficient and Robust Neural Network Inference](https://mlsanity.com/paper/2308.04753/) (2023)
- [Riemann Sum Optimization for Accurate Integrated Gradients Computation](https://mlsanity.com/paper/2410.04118/) (2024)
- [Leveraging Local Structure for Improving Model Explanations: An Information Propagation Approach](https://mlsanity.com/paper/2409.16429/) (2024)
- [Enhancing Visual Feature Attribution via Weighted Integrated Gradients](https://mlsanity.com/paper/2505.03201/) (2025)
- [Training for Trustworthy Saliency Maps: Adversarial Training Meets Feature-Map Smoothing](https://mlsanity.com/paper/2603.07302/) (2026)
- [IG-Lens: Exact Additive Probability Attribution Across Transformer Layers via Telescoping Integrated Gradients](https://mlsanity.com/paper/2606.29693/) (2026)

## Abstract (arXiv)

Integrated Gradients (IG) as well as its variants are well-known techniques for interpreting the decisions of deep neural networks. While IG-based approaches attain state-of-the-art performance, they often integrate noise into their explanation saliency maps, which reduce their interpretability. To minimize the noise, we examine the source of the noise analytically and propose a new approach to reduce the explanation noise based on our analytical findings. We propose the Important Direction Gradient Integration (IDGI) framework, which can be easily incorporated into any IG-based method that uses the Reimann Integration for integrated gradient computation. Extensive experiments with three IG-based methods show that IDGI improves them drastically on numerous interpretability metrics.