A Multimodal XAI Framework for Trustworthy CNNs and Bias Detection in Deep Representation Learning
This work addresses the need for trustworthy AI in sensitive domains by enhancing transparency and fairness, though it is incremental as it builds on existing XAI methods.
The paper tackled the problem of latent biases and limited trustworthiness in deep neural networks for high-stakes applications by proposing a multimodal Explainable AI framework, achieving 93.2% classification accuracy, 91.6% F1-score, and 78.1% explanation fidelity on multimodal MNIST extensions.
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.