DeceptionNet - Network-Driven Domain Randomization

Sergey Zakharov
Sergey Zakharov

ICCV, pp. 532-541, 2019.

Cited by: 12|Views16
EI

Abstract:

We present a novel approach to tackle domain adaptation between synthetic and real data. Instead of employing 'blind' domain randomization, i.e. augmenting synthetic renderings with random backgrounds or changing illumination and colorization, we leverage the task network as its own adversarial guide towards useful augmentations that ma...More

Code:

Data:

Full Text
Bibtex
Your rating :
0

 

Tags
Comments