Closed samyak0210 closed 4 years ago
Yes, in the object detection field, and especially in these days, there are many paper exploring using iou-based loss for bounding box regression. The giou loss for object detection was proposed earlier, and you can find the paper here.
I am closing this since you might have figured it out.
Can G-IOU be used as a loss function? Actually I am training a bounding box prediction model and using GIOU as a loss function but after some few iterations of the first epoch of training, I am getting constant values.