I guess you can have similar effect by tuning the weight coefficient of your cost function and use more complex matching strategy in the cost calculation. YOLO cost function is pretty complex. So the question is whether the coefficient is easier to tune than the negative mining. I don’t have any data to say whether any extra negative mining may help in YOLO that cannot be done by tuning those coefficient.

Written by

Deep Learning

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store