# Evaluation of Saliency-based Explainability Method

arXiv: https://arxiv.org/abs/2106.12773 · HTML: https://mlsanity.com/paper/2106.12773/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 25 references that are in the map.
- First posted on arXiv 24 Jun 2021.

## Builds on (most cited first, 16 of 16)

- [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)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (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)
- [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)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [Top-down Neural Attention by Excitation Backprop](https://mlsanity.com/paper/1608.00507/) (2016)
- [Full-Gradient Representation for Neural Network Visualization](https://mlsanity.com/paper/1905.00780/) (2019)
- [When Explanations Lie: Why Many Modified BP Attributions Fail](https://mlsanity.com/paper/1912.09818/) (2019)
- [Evaluating Saliency Map Explanations for Convolutional Neural Networks: A User Study](https://mlsanity.com/paper/2002.00772/) (2020)
- [Do semantic parts emerge in Convolutional Neural Networks?](https://mlsanity.com/paper/1607.03738/) (2016)
- [Quantitative Evaluations on Saliency Methods: An Experimental Study](https://mlsanity.com/paper/2012.15616/) (2020)

## Built on by (most cited first, 5 of 5)

- [Machine Learning-Aided Operations and Communications of Unmanned Aerial Vehicles: A Contemporary Survey](https://mlsanity.com/paper/2211.04324/) (2022)
- [eXpLogic: Explaining Logic Types and Patterns in DiffLogic Networks](https://mlsanity.com/paper/2503.09910/) (2025)
- [From Abstract to Actionable: Pairwise Shapley Values for Explainable AI](https://mlsanity.com/paper/2502.12525/) (2025)
- [One-Shot Clustering for Federated Learning](https://mlsanity.com/paper/2503.04231/) (2025)
- [One-Shot Clustering for Federated Learning Under Clustering-Agnostic Assumption](https://mlsanity.com/paper/2509.01587/) (2025)

## Abstract (arXiv)

A particular class of Explainable AI (XAI) methods provide saliency maps to highlight part of the image a Convolutional Neural Network (CNN) model looks at to classify the image as a way to explain its working. These methods provide an intuitive way for users to understand predictions made by CNNs. Other than quantitative computational tests, the vast majority of evidence to highlight that the methods are valuable is anecdotal. Given that humans would be the end-users of such methods, we devise three human subject experiments through which we gauge the effectiveness of these saliency-based explainability methods.