Multi-Head Explainer: A General Framework to Improve Explainability in CNNs and Transformers
This addresses the need for better interpretability in deep learning models for domains like medical imaging and text classification, though it appears incremental as it builds on existing architectures.
The paper tackled the problem of enhancing explainability and accuracy in CNNs and Transformers by introducing the Multi-Head Explainer (MHEX) framework, which improved classification accuracy and produced detailed saliency maps on benchmark datasets in medical imaging and text classification.
In this study, we introduce the Multi-Head Explainer (MHEX), a versatile and modular framework that enhances both the explainability and accuracy of Convolutional Neural Networks (CNNs) and Transformer-based models. MHEX consists of three core components: an Attention Gate that dynamically highlights task-relevant features, Deep Supervision that guides early layers to capture fine-grained details pertinent to the target class, and an Equivalent Matrix that unifies refined local and global representations to generate comprehensive saliency maps. Our approach demonstrates superior compatibility, enabling effortless integration into existing residual networks like ResNet and Transformer architectures such as BERT with minimal modifications. Extensive experiments on benchmark datasets in medical imaging and text classification show that MHEX not only improves classification accuracy but also produces highly interpretable and detailed saliency scores.