Large Scale Few Shot Learning via Multi modal Knowledge Discovery

Shuo Wang
Shuo Wang
Jun Yue
Jun Yue
Jianzhuang Liu
Jianzhuang Liu
Qi Tian
Qi Tian

European Conference on Computer Vision, pp. 718-734, 2020.

Cited by: 0|Bibtex|Views22

Abstract:

Large-scale few-shot learning aims at identifying hundreds of novel object categories where each category has only a few samples. It is a challenging problem since (1) the identifying process is susceptible to over-fitting with limited samples of an object, and (2) the sample imbalance between a base (known knowledge) category and a novel...More

Code:

Data:

Your rating :
0

 

Tags
Comments