2
$\begingroup$

I have been reading more about computer vision and I'm bothered by YOLO and similar deep learning architectures.

The thing I am confused about is how non-class image sections are dealt with. In particular, it's not clear to me at all why YOLO doesn't consider every part of an image a possible class.

What actually sets the cutoff for detection and then classification?

$\endgroup$

2 Answers 2

2
$\begingroup$

The output of YOLO is (x,y,w,h,confidence,class). The confidence value presents whether the rectangle holds an object, the rectangle is non-classed when confidence is low.

The class value will be used, only when confidence is high.

$\endgroup$
0
$\begingroup$

As of now, it is not possible to detect the non-class object. You have to train that non-class object again then the model will detect.

$\endgroup$
1
  • $\begingroup$ Your answer could be improved with additional supporting information. Please edit to add further details, such as citations or documentation, so that others can confirm that your answer is correct. You can find more information on how to write good answers in the help center. $\endgroup$
    – Community Bot
    Sep 22, 2022 at 7:28

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .