DeceptionNet - Network-Driven Domain Randomization
ICCV, pp. 532-541, 2019.
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
PPT (Upload PPT)