首页> Proceedings of SPIE--the International Society for Optical Engineering> ProtoSAM-2D: 2D Semantic Segment Anything Model with Mask-Level Prototype-Learning and Distillation.

ProtoSAM-2D: 2D Semantic Segment Anything Model with Mask-Level Prototype-Learning and Distillation.

导出 LinkOut

翻译打印收藏纠错

第一作者： Yiqing,Shen

第一单位： Department of Computer Science, Johns Hopkins University, Baltimore, USA.

作者： Yiqing,Shen ^[1] ; David,Dreizin ^[2] ; Blanca,Inigo ^[1] ; Mathias,Unberath ^[1]

作者单位： Department of Computer Science, Johns Hopkins University, Baltimore, USA. ^[1] University of Maryland School of Medicine and R Adams Cowley Shock Trauma Center, Baltimore, USA. ^[2]

关键词 Deep Learning Foundation Models Prototype-based Learning Segment Anything Model

DOI 10.1117/12.3047044

PMID 40678353

发布时间 2025-07-22

翻译满意度评价：

准确一般字义偏差语意偏离译文作用小提交

浏览0

Proceedings of SPIE--the International Society for Optical Engineering

2025年13406卷

相似文献

中文期刊
外文期刊
学位论文
会议论文

浏览0

点击下载本期目录封面

Proceedings of SPIE--the International Society for Optical Engineering

2025年13406卷

检索历史清除

ProtoSAM-2D: 2D Semantic Segment Anything Model with Mask-Level Prototype-Learning and Distillation.

Proceedings of SPIE--the International Society for Optical Engineering

相似文献

同项目论文

Proceedings of SPIE--the International Society for Optical Engineering

相关期刊

参考文献：
指定格式：	NoteExpress EndNote RefWorks NoteFirst

检索历史 清除

ProtoSAM-2D: 2D Semantic Segment Anything Model with Mask-Level Prototype-Learning and Distillation.

Proceedings of SPIE--the International Society for Optical Engineering

相似文献

同项目论文

Proceedings of SPIE--the International Society for Optical Engineering

相关期刊

检索历史清除