Non-Max Suppression

Zoooeee · July 25, 2021, 10:41am

I have a quick question about non-max suppression. Why not just pick the highest score directly from all the bounding boxes and then discard all the remaining ones? Why do we choose the more complex iterative procedure of picking the highest, discarding the high IOU boxes and so on. Thank you.

ai_curious · July 25, 2021, 11:13am

What is the total number of objects you could detect per image following the max score only approach? Is that aligned with the design objective of YOLO?

There is an elaboration of the answer within this thread on the implication of grid cells and anchor boxes in YOLO

Topic		Replies	Views
YOLO non max suppression in training? Convolutional Neural Networks	3	634	July 10, 2021
Question about Non-max suppression algorithm Convolutional Neural Networks	5	535	January 6, 2023
Non_max_suppression and the argument of classes Convolutional Neural Networks	1	559	March 7, 2023
W3: Question with non max suppression and classes Convolutional Neural Networks	7	1124	October 10, 2023
Non-max suppression C4W3 assignment (car detection with YOLO) Convolutional Neural Networks	8	851	May 6, 2023

Non-Max Suppression

Related topics