Multi-Head Explainer: A General Framework to Improve Explainability in CNNs and Transformers

Add to your list(s) Download to your calendar using vCal

• Bohang Sun(Bob) University of Electronic Science and Technology of China
• Friday 17 January 2025, 14:00-15:00
• Lecture Theatre 2, Computer Laboratory, William Gates Building.

If you have a question about this talk, please contact Pietro Lio.

online talk: https://meet.google.com/fma-rwwp-zfx

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.

This talk is part of the Foundation AI series.

This talk is included in these lists:

• Lecture Theatre 2, Computer Laboratory, William Gates Building

Note that ex-directory lists are not shown.