Infinite Mixture Prototypes for Few-Shot Learning

Kelsey R. Allen
Kelsey R. Allen
Hanul Shin
Hanul Shin

arXiv: Learning, 2019.

Cited by: 25|Bibtex|Views193
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

We propose infinite mixture prototypes to adaptively represent both simple and complex data distributions for few-shot learning. Our infinite mixture prototypes represent each class by a set of clusters, unlike existing prototypical methods that represent each class by a single cluster. By inferring the number of clusters, infinite mixtur...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments