University of Cambridge > Talks.cam > Foundation AI > Multi-Head Explainer: A General Framework to Improve Explainability in CNNs and Transformers

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

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

Download to your calendar using vCal

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

record: https://youtu.be/iuT_tkVEgA4

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:

Note that ex-directory lists are not shown.

Other lists

Average on weekdays: 8968.24827586 kWh History of science for mathmos Pharmacology Tea Club Seminars Michaelmas 2013

Other talks

The role of radiation in cancer care: a spotlight on cancers of the oesophagus, head and neck Tea and Coffee Break Group Work Title to be confirmed title and abstract tba (joint seminar with Spectral Geometry in the Clouds) Title to be confirmed
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity