国内外有哪些做小样本学习(Few-Shot Learning)的优秀团队？

链接：https://www.zhihu.com/question/426898850

编辑：深度学习与计算机视觉

声明：仅做学术分享，侵删

作者：知乎用户
https://www.zhihu.com/question/426898850/answer/1790870250

我们可以检索到小样本学习领域的学者们（排名不分先后）。

Richard S. Zemel (http://www.cs.toronto.edu/~zemel/inquiry/home.php) Professor,Department of Computer Science, University of Toronto

Kevin Swersky (http://www.cs.toronto.edu/~kswersky/) research scientist at Google Brain

Hugo Larochelle (https://mila.quebec/personne/hugo-larochelle/) Associate Professor at Google Brain

Nikos Komodakis（https://www.csd.uoc.gr/~hannover/LabsiteDraft/komodakis.html） postdoctoral research associate at the Computer Science Department of University of Crete.

Spyros Gidaris（https://scholar.google.com/citations?user=7atfg7EAAAAJ&hl=en）valeo ai

Zeynep Akata（https://eml-unitue.de/people/zeynep-akata）Professor of Computer Science, University of Tübingen

Trevor Darrell  (https://www2.eecs.berkeley.edu/Faculty/Homepages/darrell.html) on the faculty of the CS Division at UC Berkeley

Bernt Schiele  (https://www.mpi-inf.mpg.de/departments/computer-vision-and-machine-learning/people/bernt-schiele/) Max-Planck-Director at MPI Informatics and Professor at Saarland University

Qianru Sun（孙倩茹）（https://qianrusun.com/）  Assistant Professor Singapore Management University

Wenbin Li（李文斌） （https://cs.nju.edu.cn/liwenbin/）an Assistant Researcher of the Department of Computer Science and Technology at Nanjing University

Jiebo Luo (https://www.cs.rochester.edu/people/faculty/luo_jiebo/index.html) Data Science CoE Distinguished Researcher，Goergen Institute for Data Science

作者：知乎用户
https://www.zhihu.com/question/426898850/answer/1538362734

做few-shot的人很多,但深耕此领域并长期有产出的人不是很多！
简单列举一下自己关注过的一些researcher：

国内

• 复旦大学--Yanwei Fu

• 中国人民大学--Zhiwu Lu

• 南京大学--Wenbin Li

国外

• Surrey--Tao Xiang

• CMU--Yuxiong Wang
  

作者：CHEN
https://www.zhihu.com/question/426898850/answer/1539238592

小样本这块很乱，主要是没有一个公认的标准和定义，颇有各说各家之感。

如果说国内哪些团队做的不错，那我就推荐四川大学计算机学院院长吕建成团队吧，因为我们线下接触过，吕老师曾经用1个样本做了不少事情，吕老师的很多想法也很高屋建瓴。

吕老师这块做出的特色是引入了“特定参数分布生成方法”、“回忆生成机制”等。具体信息可以查看吕老师主页，或者知网搜索吕老师指导的相关博硕士论文。

作者：匿名用户
https://www.zhihu.com/question/426898850/answer/1793928696

北大王立威教授

• Hanzhe Hu, Shuai Bai, Aoxue Li, Jinshi Cui,Liwei Wang, “Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detection”, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2021.

• Aoxue Li, Weiran Huang, Xu Lan, Jiashi Feng, Zhenguo Li, Liwei Wang, “Boosting Few-Shot Learning With Adaptive Margin Loss”, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2020.

• Tiange Luo, Aoxue Li, Tao Xiang, Weiran Huang, Liwei Wang, “Few-Shot Learning with Global Class Representations”, International Conference on Computer Vision (ICCV), 2019.

• Aoxue Li, Tiange Luo, Zhiwu Lu, Tao Xiang, Liwei Wang, “Large-Scale Few-shot Learning: Knowledge Transfer With Class Hierarchy”, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2019.

作者：匿名用户

https://www.zhihu.com/question/426898850/answer/1568770098

这个方向其实体量不大，做是可以做，但是不太可能会有一直专门在这个方向工作的人，这个问题一般只是一个团队研究内容的一个分支。

☆ END ☆

如果看到这里，说明你喜欢这篇文章，请转发、点赞。微信搜索「uncle_pn」，欢迎添加小编微信「 mthler」，每日朋友圈更新一篇高质量博文。

↓扫描二维码添加小编↓