Envisioning MedCLIP: A Deep Dive into Explainability for Medical Vision-Language Models

arXiv:2403.18996v1 Announce Type: new
Abstract: Explaining Deep Learning models is becoming increasingly important in the face of daily emerging multimodal models, particularly in safety-critical domains like medical imaging. However, the lack of detailed investigations into the performance of explainability methods on these models is widening the gap between their development and safe deployment. In this work, we analyze the performance of various explainable AI methods on a vision-language model, MedCLIP, to demystify its inner workings. We also provide a simple …

abstract arxiv cs.cv daily deep dive deep learning domains explainability face gap however imaging investigations language language models medical medical imaging multimodal multimodal models performance safety safety-critical type vision vision-language models