Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

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

Sovon Chakraborty1, Shakib Mahmud Dipto1, Kevin R Pilkiewicz2

  • 1Department of Computer Science, Old Dominion University, Norfolk, VA 23529, USA.

Entropy (Basel, Switzerland)
|May 26, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

GramSeq-DTA: A Grammar-Based Drug-Target Affinity Prediction Approach Fusing Gene Expression Information.

Biomolecules·2025
Same author

Heterogeneous Clustering of Multiomics Data for Breast Cancer Subgroup Classification and Detection.

International journal of molecular sciences·2025
Same author

Probing Asymmetric Interactions with Time-Separated Mutual Information: A Case Study Using Golden Shiners.

Entropy (Basel, Switzerland)·2024
Same author

The Dynamic Spatial Structure of Flocks.

Entropy (Basel, Switzerland)·2024
Same author

Evaluation of individual and ensemble probabilistic forecasts of COVID-19 mortality in the United States.

Proceedings of the National Academy of Sciences of the United States of America·2022
Same author

Relevant and Non-Redundant Feature Selection for Cancer Classification and Subtype Detection.

Cancers·2021
Same journal

Research on a Regional Availability Evaluation Model for Road-Area High-Entropy Energy Based on Synergy Factors.

Entropy (Basel, Switzerland)·2026
Same journal

Atmospheric Turbulence Channel Modeling and Performance Analysis of a CO-ZP-OFDM Coherent Optical Communication System for UAV Air-to-Ground Scenarios.

Entropy (Basel, Switzerland)·2026
Same journal

Information Geometry and Asymptotic Theory for SMML Estimators.

Entropy (Basel, Switzerland)·2026
Same journal

Correlation Entropy and Power-Law Kinetics.

Entropy (Basel, Switzerland)·2026
Same journal

Research on the Contagion of Systemic Financial Risk Under the Impact of Climate Risks-From the Perspective of Complex Networks and Machine Learning.

Entropy (Basel, Switzerland)·2026
Same journal

The Statistical-Mechanical Meaning of the Wave Function of Quantum Mechanics.

Entropy (Basel, Switzerland)·2026
See all related articles

Explainable AI (XAI) methods help trust black-box models. This study compares four XAI techniques (PEEK, LRP, GRAD-CAM, LIME) for image classification, finding limited consensus on critical features but highlighting Grad-CAM

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Black-box machine learning models lack transparency, hindering trust and adoption.
  • Explainable AI (XAI) methods are crucial for providing human-understandable justifications for model decisions.
  • Selecting the appropriate XAI technique is vital for specific machine learning tasks.

Purpose of the Study:

  • To evaluate and compare the performance of four XAI techniques: PEEK, LRP, GRAD-CAM, and LIME.
  • To assess these XAI methods on image classification tasks using the Oxford IIT pet dataset.
  • To analyze the performance, robustness, generalizability, noise stability, and computational efficiency of each XAI method.

Main Methods:

  • Utilized the Oxford IIT pet dataset (7390 images) for training custom Convolutional Neural Network (CNN) and VGG16 models.
Keywords:
Grad-CAMLIMELRPPEEKXAIimage classificationinterpretability

Related Experiment Videos

  • Analyzed saliency maps generated by PEEK, LRP, GRAD-CAM, and LIME to identify critical image regions for classification.
  • Employed noise analysis, robustness checks, run-time measurements, and faithfulness metrics for comprehensive evaluation.

    • Main Results:

    • XAI methods generally identified intuitive, critical features (e.g., outlines, faces, eyes) for accurate classification.
    • Significant variation and marginal consensus were observed among XAI methods in pinpointing these critical features.
    • Grad-CAM showed strong robustness and stability with the VGG16 model, but inconsistent performance with a shallow CNN.

    Conclusions:

    • While XAI methods offer insights into black-box model reasoning, their consensus on critical features is limited.
    • Grad-CAM shows promise for robust explanations in complex models like VGG16.
    • Further research is needed to improve consensus and tailor XAI methods for reliable image classification explanations.