Online Object Representations with Contrastive Learning

Sören Pirk
Sören Pirk
Mohi Khansari
Mohi Khansari
Corey Lynch
Corey Lynch

CoRR, 2019.

Cited by: 0|Bibtex|Views78
EI
Other Links: dblp.uni-trier.de|arxiv.org

Abstract:

We propose a self-supervised approach for learning representations of objects from monocular videos and demonstrate it is particularly useful in situated settings such as robotics. The main contributions of this paper are: 1) a self-supervising objective trained with contrastive learning that can discover and disentangle object attribut...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments