Object Detection With Synthetic Data

Reduce the domain gap with domain randomization

In this post, we’ll explore how we can improve the accuracy of object detection models that have been trained solely on synthetic data.

Why machine learning? Why simulate data?

Since the resurgence of deep learning for computer vision through AlexNet in 2012, we have seen improvement after improvement — deeper networks, new architectures, more availability in data — with records being broken for accuracy and…