R-Cut: Enhancing Explainability in Vision Transformers with Relationship Weighted Out and Cut

R-Cut: Enhancing Explainability in Vision Transformers with Relationship Weighted Out and Cut

Transformer-based models have gained popularity in the field of natural language processing (NLP) and are extensively utilized in computer vision tasks and multi-modal models such as GPT4. This paper presents a novel method to enhance the explainability of transformer-based image classification mode...

Full description

Bibliographic Details
Main Authors: Yingjie Niu, Ming Ding, Maoning Ge, Robin Karlsson, Yuxiao Zhang, Alexander Carballo, Kazuya Takeda
Format: Article
Language:English
Published: MDPI AG 2024-04-01
Series:Sensors
Subjects:
visual explanation
vision transformer
post hoc explanation
class-specific explanation
Online Access:https://www.mdpi.com/1424-8220/24/9/2695

Internet

https://www.mdpi.com/1424-8220/24/9/2695

Similar Items