提出多头解释框架，让卷积网络和Transformer更准确且可解释。
Multi-Head Explainer: A General Framework to Improve Explainability in CNNs and Transformers
- 用注意力门控动态聚焦关键特征，提升模型关注重点。
- 在医学影像与文本分类任务中，准确率提升且热力图细节更丰富。
- 可无缝接入ResNet、BERT等主流模型，适合需要可解释性的研究者。
本研究提出多头解释器（MHEX），一种通用且模块化的框架，用于提升卷积神经网络（CNN）和基于Transformer模型的可解释性与准确性。MHEX包含三个核心组件：注意力门控，动态突出任务相关特征；深度监督，引导早期层捕捉目标类别相关的细粒度信息；等效矩阵，融合优化后的局部与全局表征以生成全面的显著性图。该方法具备优异的兼容性，可几乎无修改地集成到ResNet等残差网络及BERT等Transformer架构中。在医学影像与文本分类的基准数据集上进行的大量实验表明，MHEX不仅提升了分类准确率，还生成了高度可解释且细节丰富的显著性评分。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。