Generalized Convolutional Forest Networks for Domain Generalization and Visual Recognition

ICLR, 2020.

Cited by: 3|Views56
EI
Weibo:
We propose the Generalized Convolutional Forest Network method which learns the generalized feature space iteratively such that the discrimination strength of each tree classifier is increased while the correlation is suppressed

Abstract:

When constructing random forests, it is of prime importance to ensure high accuracy and low correlation of individual tree classifiers for good performance. Nevertheless, it is typically difficult for existing random forest methods to strike a good balance between these conflicting factors. In this work, we propose a generalized convoluti...More

Code:

Data:

0
Your rating :
0

 

Tags
Comments