A Multimodal XAI Framework for Trustworthy CNNs and Bias Detection in Deep Representation Learning

Noor Islam S. Mohammad
10/14/2025
cs.LGcs.AI

No confident code implementation found for this paper.

Abstract

Standard benchmark datasets, such as MNIST, often fail to expose latent biases and multimodal feature complexities, limiting the trustworthiness of deep neural networks in high-stakes applications. We propose a novel multimodal Explainable AI (XAI) framework that unifies attention-augmented feature fusion, Grad-CAM++-based local explanations, and a Reveal-to-Revise feedback loop for bias detection and mitigation. Evaluated on multimodal extensions of MNIST, our approach achieves 93.2% classification accuracy, 91.6% F1-score, and 78.1% explanation fidelity (IoU-XAI), outperforming unimodal and non-explainable baselines. Ablation studies demonstrate that integrating interpretability with bias-aware learning enhances robustness and human alignment. Our work bridges the gap between performance, transparency, and fairness, highlighting a practical pathway for trustworthy AI in sensitive domains.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future

87% match1 repo92024

XAI-TRIS: Non-linear image benchmarks to quantify false positive post-hoc attribution of feature importance

86% match1 repo32023

AS-XAI: Self-supervised Automatic Semantic Interpretation for CNN

85% match1 repo2023

Clarifying Model Transparency: Interpretability versus Explainability in Deep Learning with MNIST and IMDB Examples

84% match2025

A Comprehensive Guide to Explainable AI: From Classical Models to LLMs

84% match1 repo522024

Explaining Explainability: Towards Deeper Actionable Insights into Deep Learning through Second-order Explainability

84% match2023

Cite this paper

@article{mohammad2025multimodal,
  title  = {A Multimodal XAI Framework for Trustworthy CNNs and Bias Detection in Deep Representation Learning},
  author = {Noor Islam S. Mohammad},
  year   = {2025},
  eprint = {2510.12957},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2510.12957v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2510.12957.svg)](https://codeofpaper.com/paper/2510.12957)

Discussion