• By Vincent Spruyt
  • February 16, 2018

figure_11

The SoftPN loss optimizes the more difficult problem by maximizing the minimum distance between negative instance and either anchor or positive.

The SoftPN loss optimizes the more difficult problem by maximizing the minimum distance between negative instance and either anchor or positive.

Subscribe To Our Newsletter

Join our mailing list to receive the latest news and updates.

You have Successfully Subscribed!