When it comes to the relationship between geospatial neural network performance and the amount of training data, do geographic differences matter?
Archives for 2019
When training a deep neural network to identify building footprints in satellite imagery, having more training data never hurts. But how much does more data help, and when is it worth the cost and difficulty of procuring it?
Using Solaris, you can fine-tune deep learning models pre-trained on overhead imagery for five minutes and achieve performance comparable to past SpaceNet Challenge prize-winners.
Now that the SpaceNet 5 dataset has been released, and the challenge is live on Topcoder, we anticipate a great many insights from this challenge into how well computer vision can automatically extract road networks and travel time estimates.
Generative Adversarial Networks (GANs) have become increasingly popular in machine learning due to their ability to mimic any distribution of data. By pitting two neural networks against each other, they are able to learn ever more subtle differences between real and synthetic data, which in turn drives the generation of ever more life-like examples, otherwise known as deep fakes.