![]() ![]() We 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. To reduce this gap, we propose 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. However, learning from synthetic images may not achieve the desired performance due to a gap between synthetic and real image distributions. With recent progress in graphics, it has become more tractable to train models on synthetic images, potentially avoiding the need for expensive annotations. Apple have published some of their artificial intelligence research, arXiv:1612.07828
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |