Zzh-tju / DIoU

Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression (AAAI 2020)

Zzh-tju/DIoU Issues

Question about calculating the derivative of DIoU
Updated 7 months ago
Hello, may I ask, how did you come up with the calculation formulas for α and v in the original CIOU paper?
Updated 10 months ago
Reproduced the simulation experiment in pytorch [Converges but different results for GIoU from the paper]
Updated 10 months ago3
About the derivative w.r.t l, r, t, b to the derivative w.r.t x, y, w, h
Closed a year ago1
Derivation of CIoU Loss equations
Updated a year ago6
Hello,have you used diou on the centernet
Updated 2 years ago3
in the ciou equa., the deviation of v wrt w and h for the scale factor sqrt(w**2+h**2) seems wrong
Updated 2 years ago13
Question regarding loss
Updated 2 years ago1
Hello, I have a question when using the code you provided
Closed 3 years ago
关于DIOU论文仿真dDIOU.m中的求导部分
Closed 3 years ago
I want to reproduce the experiment about bounding box regression in figure 1
Closed 3 years ago1
Hi，where is code of simulation experiments such as three typical cases?
Updated 3 years ago1
t, b, l, r mean what?
Closed 3 years ago1
请问test_1715k.m运行多久呢？
Updated 4 years ago7
for k=161:180
Closed 4 years ago7
matlab仿真运行
Updated 4 years ago
Quadrilateral DIOU?
Updated 4 years ago1
Radius = 3 for simulation
Closed 4 years ago2
You use Diou loss/Ciou loss only on rcnn head or both rpn and rcnn head?
Closed 4 years ago7
求助：请问为什么用darknet yolov3训练时，log日志中显示的还是giou，而且训练loss比用giou的高，请问这是啥原因呢，谢谢！
Closed 4 years ago6
txt文件获取
Closed 4 years ago6
Some confusion of the thesis
Closed 4 years ago2
DIoU.m程序的一点愚见
Closed 4 years ago
Independent PyTorch-YOLOv3 Results
Closed 4 years ago6