Closed wtiandong closed 3 years ago
This is from YOLOv2 - 2016 year: https://github.com/AlexeyAB/darknet/blob/b11af9e93b4ec225450b0dd73bdd7aaa1f2912b8/src/region_layer.c#L351
YOLO9000: Better, Faster, Stronger 25 Dec 2016: https://arxiv.org/pdf/1612.08242.pdf
Following YOLO, the objectness prediction still predicts the IOU of the ground truth and the proposed box and the class predictions predict the conditional probability of that class given that there is an object.
Losses:
OK, Thank you! @AlexeyAB It's interesting that in Yolov3 the IOU in objectness is removed, and now back in Yolov4.
objectness_smooth
slightly increases AP (AP50...95) but decreases AP50
objectness_smooth
was forcibly enabled in YOLOv2, while it is optional in YOLOv4 (enabled in Scaled-YOLOv4 and disabled in YOLOv4)
objectness_smooth
slightly increases AP (AP50...95) but decreases AP50objectness_smooth
was forcibly enabled in YOLOv2, while it is optional in YOLOv4 (enabled in Scaled-YOLOv4 and disabled in YOLOv4)
OK,thank you!
❔Question
Could you please give some references that use IOU as objectness labels?
Additional context
I notice it is called objectness smooth in yolov4 codes, but I can't find who is first using this method or in any papers, not even in the yolov4 paper. Thank you.