mlsanityData to 7 Oct 2026

Evaluation of Saliency-based Explainability Method

arXiv 2106.12773 ↗First posted 24 Jun 2021cs.LGcited by 5

Not on the map. Why?

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.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 16 of its 25 references that are in the map. First posted on arXiv 24 Jun 2021.

Builds on

16 of 25 references.

References · 16

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  4. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  5. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  6. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  7. 2018Sanity Checks for Saliency Mapscited by 1,149
  8. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  9. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 703
  10. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
  11. 2016Top-down Neural Attention by Excitation Backpropcited by 318
  12. 2019Full-Gradient Representation for Neural Network Visualizationcited by 189
4 more
  1. 2019When Explanations Lie: Why Many Modified BP Attributions Failcited by 92
  2. 2020Evaluating Saliency Map Explanations for Convolutional Neural Networks: A User Studycited by 86
  3. 2016Do semantic parts emerge in Convolutional Neural Networks?cited by 23
  4. 2020Quantitative Evaluations on Saliency Methods: An Experimental Studycited by 10

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 0; 2024: 0; 2025: 4.

5 papers.

  1. 2022Machine Learning-Aided Operations and Communications of Unmanned Aerial Vehicles: A Contemporary Surveycited by 27
  2. 2025eXpLogic: Explaining Logic Types and Patterns in DiffLogic Networkscited by 3
  3. 2025From Abstract to Actionable: Pairwise Shapley Values for Explainable AIcited by 0
  4. 2025One-Shot Clustering for Federated Learningcited by 0
  5. 2025One-Shot Clustering for Federated Learning Under Clustering-Agnostic Assumptioncited by 0