Learning from Simulated and Unsupervised Images


This paper aims to reduce the gap between real and synthetic training images by introduces a new method called Simulated+Unsupervised (S+U) learning, where the task is to learn a model to improve the realism of a simulator’s output using unlabeled real data, while preserving the annotation information from the simulator.The authors develop a method for S+U learning that uses an adversarial network similar to Generative Adversarial Networks (GANs), but with synthetic images as inputs instead of random vectors. An example if this training method can be found in the SimGAN repo linked to above.


Want to receive more content like this in your inbox?