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
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
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“By contrast, feature- or concept-based explanations appeared only in systems incorporating conventional predictive components amenable to attribution, such as saliency maps, concept bottleneck representations, or SHAP analyses over structured variables [31,32,33].”
From Explainable Agentic Artificial Intelligence in Healthcare: A Scoping Review (2026) · cites this paper as [32]
Citations
Cites
Advances in Neural Information Processing Systems 19
(2007) · The MIT Press eBooks · doi:10.52202/085713 · Cited by 15,539
Correlation Coefficients: Appropriate Use and Interpretation
Schober, P., Boer, C., & Schwarte, L. A. (2018) · Anesthesia & Analgesia · doi:10.1213/ane.0000000000002864 · Cited by 10,986 · cited 1×
“The correlation score [28], denoted as CS, is calculated using the following formula (1): where H i represents the importance value in the original XAI heatmap for the i -th pixel, M i represents the importance value in the XAI heatmap after applying the occlusion mask for the same pixel, H is the…”
Tschandl, P., Rosendahl, C., & Kittler, H. (2018) · Scientific Data · doi:10.1038/sdata.2018.161 · Cited by 3,628
Sanity Checks for Saliency Maps
Adebayo, J., Gilmer, J., Muelly, M., Goodfellow, I., Hardt, M., & Kim, B. (2018) · arXiv · doi:10.48550/arxiv.1810.03292 · Cited by 1,294
Yang, G., Ye, Q., & Xia, J. (2022) · Information Fusion · doi:10.1016/j.inffus.2021.07.016 · Cited by 717
Understanding diagnostic tests 1: sensitivity, specificity and predictive values
Akobeng, A. K. (2007) · Acta Paediatrica · doi:10.1111/j.1651-2227.2006.00180.x · Cited by 707
Evaluating the quality of machine learning explanations: a survey on methods and metrics
Zhou, J., Gandomi, A. H., Chen, F., & Holzinger, A. (2021) · Electronics · doi:10.3390/electronics10050593 · Cited by 606 · cited 1×
“Fidelity measures the agreement between an XAI explanation and the actual model prediction [3].”
Nauta, M., Trienes, J., Pathak, S., Nguyen, E., Peters, M., Schmitt, Y., Schlötterer, J., van Keulen, M., & Seifert, C. (2023) · ACM Computing Surveys · doi:10.1145/3583558 · Cited by 590
Towards Faithfully Interpretable NLP Systems: How Should We Define and Evaluate Faithfulness?
Jacovi, A., & Goldberg, Y. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.386 · Cited by 503
The Shapley Value in Machine Learning
Rozemberczki, B., Watson, L., Bayer, P., Yang, H.-T., Kiss, O., Nilsson, S., & Sarkar, R. (2022) · arXiv · doi:10.48550/arxiv.2202.05594 · Cited by 312
Research works printed but not linked: 1
- Oksuz, 2023, AUTOLYCUS: Exploiting Explainable AI (XAI) for Model Extraction Attacks against Decision Tree Models, ArXiv, abs/2302.02162 · arXiv
Cited by
Multimodal skin lesion classification for early cancer diagnosis using deep learning
Gabani, V., Navamani, T. M., Shyamala, K., & Rajpal, V. K. V. (2026) · Frontiers in Physiology · doi:10.3389/fphys.2026.1717517 · Cited by 16
Li, M., Jiang, Y., Cao, G., Xu, T., & Guo, R. (2025) · Scientific Reports · doi:10.1038/s41598-025-30184-1 · Cited by 12
Improving skin lesion classification through saliency-guided loss functions
Dakhli, R., & Barhoumi, W. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.110299 · Cited by 6
Self-citationExplainable Agentic Artificial Intelligence in Healthcare: A Scoping Review
Collaco, B. G., Prabha, S., Gomez-Cabello, C. A., Haider, S. A., Genovese, A., Wood, N. G., Gopala, N., Raman, R., Hester, E. O., & Forte, A. J. (2026) · Bioengineering · doi:10.3390/bioengineering13050513 · Cited by 3
Buck, A., Cosma, G., Phillips, I. W., Conway, P., & Baker, P. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.19017 · Cited by 3
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.