Loss Function for Object Detection Regression
In object detection, loss = classification loss + bounding box regression loss Bounding box regression loss development: Smooth L1 loss-->IoU loss --> GIoU Loss --> DIoU Loss -->CIoU Loss 1. Smooth L1 loss (proposed in Fast RCNN): x: difference of predicted bounding box and the ground truth; L1 = |x|dL2(x)/x = 2x L2 = x^2 smoothL1(x) = 0.5x^2 if |x|<1 = |x|-0.5 otherwise Derivatives of the above three loss function: dL1(x)/x = 1 if x >= 0 = -1 otherwise dL2(x)/x = 2x dsmoothL1(x) = x if |x| < 1 = +-1 otherwise From above, the derivative of L1 los s is constant, when x becomes small in late training and learning rate remains same, the loss function will fluctuate around certain value and...