BriefGPT.xyz
May, 2024
预训练视觉语言模型中的伪提示生成,面向多标签医学图像分类
Pseudo-Prompt Generating in Pre-trained Vision-Language Models for Multi-Label Medical Image Classification
HTML
PDF
Yaoqin Ye, Junjie Zhang, Hongwei Shi
TL;DR
该研究介绍了一个新的提高医学图像识别性能的方法,利用预训练视觉-语言模型和伪提示生成来实现多标签分类和自动诊断,对比实验证明了其在多标签胸部放射图数据集上的卓越性能。
Abstract
The task of
medical image recognition
is notably complicated by the presence of varied and multiple pathological indications, presenting a unique challenge in
multi-label classification
with unseen labels. This c
→