谷歌浏览器插件
订阅小程序
在清言上使用

Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks

Computer Vision and Pattern Recognition(2024)

引用 0|浏览93
暂无评分
关键词
Vision Tasks,Computer Vision,Object Detection,Transfer Learning,Annotation Data,Task Instructions,Visual Model,Multi-task Learning,Comprehension Task,Image Annotation,Comprehensive Annotation,Diverse Tasks,Foundation Model,Simple Instructions,Spatial Hierarchy,Model Specification,Image Classification,Visual Task,Unified Model,Bounding Box,Universal Representation,Text Annotation,Level Of Granularity,Iterative Refinement,Wide Range Of Tasks,Tokenized,Noun Phrase,Text For Details,Range Of Tasks,Language Model
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要