The 1st Visual Intelligence Seminar on Few-shot Learning

发布者:刘铁江发布时间:2021-01-27浏览次数:2040

Summary

DNNs have shown remarkable success in many computer vision and machine learning tasks. Despite a wide range of impressive results, current DNN based methods typically depend on massive amounts of accurately annotated training data to achieve high performance. DNNs lack the ability of learning from limited exemplars and fast generalizing to new tasks. 

The Visual Intelligence Group in School of Data Science, Fudan University will hold the 1st Visual Intelligence Seminar on Few-shot Learning on January 29, 2021. We invite several distinguished speakers to share the recent progress on few-shot learning. 

Seminar Chair: Xiangyang Xue, Yanwei Fu (yanweifu@fudan.edu.cn)

Online Link: https://live.bilibili.com/22761519

Schedules

8:00 -- 8:10, Opening.

8:10 -- 9:10, Learning to Learn More with Less.

    Speaker: Yuxiong Wang. 

    Host: Yanwei Fu.

9:10 -- 10:10: Meta-Learning: Representations and Objectives.

    Speaker: Timothy M. Hospedales. 

    Host: Yanwei Fu.

10:10 -- 10:30, Break and Panel Discussion of Speakers in the Morning Session.


10:30 -- 11:30, 自监督学习进展、有效性初探及展望.

    Speaker: Songcan Chen. 

    Host: Xiangyang Xue.

11:30 -- 12:10, Towards Good Practices in Self-Supervised Representation Learning.

    Speaker: Yi Zhu. 

    Host: Li Zhang.


13:30 -- 14:30, New Meta-Learning Paradigms for Few-Shot Learning.

    Speaker: Zhiwu Lu. 

    Host: Yanwei Fu.

14:30 -- 15:10, Learning universal representation for scene understanding.

    Speaker: Li Zhang. 

    Host: Xiangyang Xue.

15:10 -- 15:50, Unsupervised Learning of 3D Objects from Images.

    Speaker: Shangzhe Wu. 

    Host: Li Zhang.

15:50 -- 16:30, Self-supervised Representation Learning from Videos.

    Speaker: Weidi Xie. 

    Host: Li Zhang.

16:30 -- 16:40, Break and Panel Discussion of Speakers in the Afternoon Session.


16:40 -- 17:20, Video Understanding In the Wild with Incomplete Supervision.

    Speaker: Anurag Arnab. 

    Host: Li Zhang.

17:20 -- 18:20, Learning with few labeled data.

    Speaker: Tao Xiang. 

    Host: Yanwei Fu.

18:20 -- 18:40, Panel Discussion and Finish.


Speakers

图片

Anurag Arnab
Google

图片
Shangzhe Wu
Univ. of Oxford

图片
Weidi Xie
Univ. of Oxford

图片
Yi Zhu
Amazon AI

图片
Timothy Hospedales
Univ. of Edinburgh

图片
Yuxiong Wang
UIUC

图片
Songcan Chen
NUAA

图片
Zhiwu Lu
Renmin Univ.

图片
Li Zhang
Fudan Univ.

图片
Tao Xiang
Univ. of Surrey

Host

图片
Xiangyang Xue
Fudan Univ.

图片
Yanwei Fu
Fudan Univ.

图片
Li Zhang
Fudan Univ.

  

For more details, please check the seminar website:

http://www.sdspeople.fudan.edu.cn/fuyanwei/VI_seminar/fudan-vi-seminar.github.io/index.html