search

Zzh-tju / DIoU

Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression (AAAI 2020)
310 stars 50 forks source link

Question regarding loss #18

Open NiranjanRavi1993 opened 2 years ago

NiranjanRavi1993 commented 2 years ago

Hi, It's very nice work. I was experimenting with my custom loss function with this simulation and have a couple of questions.

  1. In dIbox calculation, the line is estimating s.dt. But its chooses values of r and l. Shouldn't it be the other way around?
  2. In the dDIOU.m file, lines 73 to 76 were used to find s.dx, s.dy, s.dw, s.dh. Why do we multiply the equation with "C" value? Are they variables used to normalize?

Please correct if I am wrong. Thank you.

Zzh-tju commented 2 years ago
  1. This is the code of GIoU implementation https://github.com/AlexeyAB/darknet/blob/master/src/box.c#L309

This is the IoU loss paper (Unitbox: An advanced object detection network), see Eq. 5 image

  1. C is not used to normalize. It is just for derivative calculation.