EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Comparative Analysis of Explainable AI (XAI) Techniques for Transparent and Reliable Image Classification

Sovon Chakraborty iD, Shakib Mahmud Dipto iD, Kevin R Pilkiewicz iD, Michael L Mayo iD, Pratip Rana iD

Entropy · 18.05.2026 · 28 (5) · 562

DOI: 10.3390/e28050562 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 18.05.2026. Verfasst von Sovon Chakraborty und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Old Dominion University, Norfolk, VA 23529, USA. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Evaluating the trustworthiness of black-box machine learning models remains a significant methodological challenge. Their lack of transparency and interpretability limits applicability, because stakeholders often seek transparency before trusting the results of black-box machine learning models. Explainable AI (XAI) methods provide for human-understandable justifications and informed decision-making of these black-box architectures. Therefore, it is imperative to select the proper XAI model tailored to specific tasks. In this research, we focus on examining four XAI techniques: PEEK, LRP, GRAD-CAM, and LIME to understand how they perform against each other for image classification tasks. We evaluate the performance, robustness, generalizability, noise stability, and computational efficiency of these methods using a globally recognized dataset. With 7390 images, the Oxford IIT pet dataset provides a comprehensive resource for training a custom Convolutional Neural Network (CNN) and VGG16, enabling a consistent evaluation of each XAI method. First, we analyze the saliency maps of the input images and observe the regions predicted by these XAI methods, and then leverage a noise analysis approach to evaluate their performance in terms of accuracy. We further explore the robustness, run-time, and “faithfulness” metrics of each XAI method. In general, we find that these methods can identify a set of input-data features that are critical for accurate classification but also intuitive, such as the outline, face, and eyes of subjects. However, our analysis reveals only marginal consensus among XAI methods in identifying those critical features. Grad-CAM demonstrates strong robustness and stability in VGG16, but the performance on the shallow CNN model remained inconsistent.

Schlagwörter

Stichwörter der Autor:innen

Grad-CAMLIMELRPPEEKXAIimage classificationinterpretability

Autor:innen und Institutionen

  • Department of Computer Science, Old Dominion University, Norfolk, VA 23529, USA.
  • Environmental Laboratory, US Army Engineer Research and Development Center, Vicksburg, MS 39180, USA.

ORCID-Profile: Sovon Chakraborty, Shakib Mahmud Dipto, Kevin R Pilkiewicz, Michael L Mayo, Pratip Rana

Zitieren

APA

Chakraborty, S., Dipto, S. M., Pilkiewicz, K. R., Mayo, M. L., & Rana, P. (2026). A Comparative Analysis of Explainable AI (XAI) Techniques for Transparent and Reliable Image Classification. Entropy, 28(5), 562. https://doi.org/10.3390/e28050562

Vancouver

Chakraborty S, Dipto SM, Pilkiewicz KR, Mayo ML, Rana P. A Comparative Analysis of Explainable AI (XAI) Techniques for Transparent and Reliable Image Classification. Entropy. 2026;28(5):562. doi:10.3390/e28050562

BibTeX
@article{Chakraborty2026,
  author = {Chakraborty, Sovon and Dipto, Shakib Mahmud and Pilkiewicz, Kevin R and Mayo, Michael L and Rana, Pratip},
  title = {A Comparative Analysis of Explainable AI (XAI) Techniques for Transparent and Reliable Image Classification},
  journal = {Entropy},
  year = {2026},
  volume = {28},
  number = {5},
  pages = {562},
  doi = {10.3390/e28050562}
}
Kostenlos starten →