English
全部
搜索
图片
视频
地图
资讯
Copilot
更多
购物
航班
旅游
笔记本
Top stories
Sports
U.S.
Local
World
Science
Technology
Entertainment
Business
More
Politics
过去 1 小时
时间不限
过去 24 小时
过去 7 天
过去 30 天
最佳匹配
最新
30 分钟
ICLR 2026 | 澳门大学&英特灵达提出FSOD-VFM:无需训练,图扩散助力“小 ...
在目标检测领域,小样本目标检测(Few-Shot Object Detection, FSOD)一直是个“硬骨头”。传统的做法通常需要在大规模基类数据上预训练,再针对极少数的新类样本进行微调。但微调过程不仅耗时,还容易导致模型对新类样本过拟合。近日,来自澳门大学和英特灵达的研究团队提出了一种全新的框架—— FSOD-VFM 。
一些您可能无法访问的结果已被隐去。
显示无法访问的结果
今日热点
3 US service members killed
Trump says Khamenei is dead
To cease use of Anthropic AI
Protesters storm US consulate
Austin bar shooting
Dubai airport hit by strike
US surpassed 1,100 cases
Sentenced to life in prison
Legendary songwriter dies
Cher’s son charged
Middle East airports closed
Avoids federal death penalty
Joins Colorado coaching staff
Bolivia cargo plane crash
Pereira vacates UFC title
Sapp announces resignation
Falcons fire ex-MI staffer
Judge approves $345M verdict
Missing CA dad found dead
Gets 16½ years in prison
Former LSU receiver dies
Mavericks to waive Jones
To reduce flights at O’Hare
Agree to $110 billion deal
2 dead in Detroit shooting
2 trans men sue Kansas
NAACP Image Awards
Placed on paid leave
Medvedev wins Dubai title
反馈