FITA: Fine-grained Image-Text Aligner for Radiology Report Generation

arXiv:2405.00962v1 Announce Type: new
Abstract: Radiology report generation aims to automatically generate detailed and coherent descriptive reports alongside radiology images. Previous work mainly focused on refining fine-grained image features or leveraging external knowledge. However, the precise alignment of fine-grained image features with corresponding text descriptions has not been considered. This paper presents a novel method called Fine-grained Image-Text Aligner (FITA) to construct fine-grained alignment for image and text features. It has three novel designs: Image Feature Refiner (IFR), Text Feature …

abstract alignment arxiv cs.cv features fine-grained generate however image images knowledge paper radiology report reports text type work