Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 33 of the 33 references it cites were found in a registry or an index.

Toward a Quantitative Trustworthy Evaluation of Post-Hoc XAI Feature Importance Maps Using Saliency-Based Occlusion

Dakhli, Rym, Barhoumi, Walid · 2024 · 2024 IEEE/ACS 21st International Conference on Computer Systems and Applications (AICCSA)

Abstract

The increasing interest in eXplainable Artificial Intelligence (XAI) is driven by the need to understand complex deep learning models, especially in critical fields like skin cancer classification. Existing research has provided various methods to interpret and clarify the decision-making processes of complex AI systems. Among the most widely used XAI methods for deep learning models are post-hoc saliency maps, which highlight the features that contribute most to a particular prediction. However, the trustworthiness of these explanations remains a concern, particularly when interpretations can be subjective. This raises a critical question: how can we effectively evaluate the quality of explanations generated by XAI methods for deep learning predictions and how it is possible to select the appropriate saliency map method? Consequently, this issue has caused the need to develop methods for evaluating XAI. These methods aim to not only interpret model decisions but also to compare different explanation methods through qualitative and quantitative measures. This study contributes to quantitatively evaluate and compare the performances of four saliency mapping-based XAI methods, namely LIME, SHAP, Attention Maps, and Grad-CAM. In our proposal, the outputs of XAI methods are used to create occluded images using feature importance scores. The masked images will then be fed to the end-to-end classifier. To measure the performance, the main metrics that we used to assess the XAI method faithfulness are the correlation between the classifiers prediction and the features importance score before and after occlusion. The obtained results show that SHAP outperforms the other three methods and is thus more faithful. These results may help indicate that SHAP is the most suitable XAI method that can explain skin lesion classification through InceptionResnetV2 model.

Overview

Integrity signals

Registry

Crossref · 10.1109/aiccsa63423.2024.10912611

Cites

33 of 33 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 33 references

Research works printed but not linked: 1

  1. Oksuz, 2023, AUTOLYCUS: Exploiting Explainable AI (XAI) for Model Extraction Attacks against Decision Tree Models, ArXiv, abs/2302.02162 · arXiv

Cited by

See all 13

Metadata

Authors
Dakhli, R., & Barhoumi, W.
Affiliations
  • Tunis El Manar University (TN)
  • University of Carthage (TN)
Venue
2024 IEEE/ACS 21st International Conference on Computer Systems and Applications (AICCSA)
Publisher
IEEE
Published
2024-10-22
Pages
1-8
OpenAlex
W4408325998
Cited by
5
References
33
Citations by year
2026: 3 · 2025: 2
FWCI
1.44
Type
conference paper
Language
en
Open access
closed
Locations
IEEE/ACS International Conference on Computer Systems and Applications (AICCSA) (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
  • Physical Sciences › Computer Science › Software › Software Testing and Debugging Techniques
  • Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
Keywords
explainable AI, saliency maps, occlusion, XAI evaluation, faithfulness, SHAP, lime, Grad-CAM, attention maps, skin lesion classification, skin cancer classification, InceptionResNetV2, deep learning interpretability

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Toward a Quantitative Trustworthy Evaluation of Post-Hoc XAI Feature Importance Maps Using Saliency-Based Occlusion. https://app.cochat.ai/papers/10.1109/aiccsa63423.2024.10912611
The paper
Dakhli, R., & Barhoumi, W. (2024). Toward a Quantitative Trustworthy Evaluation of Post-Hoc XAI Feature Importance Maps Using Saliency-Based Occlusion. 2024 IEEE/ACS 21st International Conference on Computer Systems and Applications (AICCSA). https://doi.org/10.1109/aiccsa63423.2024.10912611

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.