DeceptionNet: Network-Driven Domain Randomization
International Conference on Computer Vision, pp. 532-541, 2019.
We present a novel approach to tackle domain adaptation between synthetic and real data. Instead of employing u0027blindu0027 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 t...More
PPT (Upload PPT)