Compositional Few-Shot Recognition with Primitive Discovery and Enhancing

Zou Yixiong
Zou Yixiong
Chen Ke
Chen Ke
Wang Yaowei
Wang Yaowei
Cited by: 0|Views66

Abstract:

Few-shot learning (FSL) aims at recognizing novel classes given only few training samples, which still remains a great challenge for deep learning. However, humans can easily recognize novel classes with only few samples. A key component of such ability is the compositional recognition that human can perform, which has been well studied...More

Code:

Data:

Full Text
Bibtex
Your rating :
0

 

Tags
Comments