Although 2D camera data is used to teach autonomous vehicles to find their way from Point A to PointB, it comes with its own set of drawbacks.
Choosing an appropriate loss function is important as it affects the ability of the algorithm to produce optimum results as fast as possible.
The most important thing that the computer vision expert does is to decide which image annotation type is needed to build the most accurate model(s) for object detection.
I have briefly written about the ways you can start gathering training data. This depends majorly on the use case you plan to work on.
Sunday Afternoon. You come across a magazine ad for solitaires, but it is the model wearing a perfect white sundress that catches your attention. What if you could take a picture of the dress and upload it, so an app could help you find a dress just like that one?