MixNMatch icon indicating copy to clipboard operation
MixNMatch copied to clipboard

What is the Bounding box?

Open fanghao123-qw opened this issue 2 years ago • 3 comments

I finished reading this paper . the paper said we only require a loose bounding box around the object to model background, But the author didn't explain it in detail. and i have some questions 1.How we define the bounding box,what is it used for? 2.what should i do to get the bounding box if i wanna train my own dataset?

i‘m looking forward to your reply。

fanghao123-qw avatar Dec 15 '21 08:12 fanghao123-qw

1, bounding boxes are used in the background stage such that the background discriminator can only see background region. 2, If you dataset does not come with box annotations, then you can use a pretrained detector to get bounding boxes.

Yuheng-Li avatar Dec 15 '21 17:12 Yuheng-Li

I am going to detect the boundary. What is the four parameters specified in the paper? like Upper left corner or sth else?

fanghao123-qw avatar Dec 20 '21 06:12 fanghao123-qw

Please follow the bounding box format in the CUB dataset http://www.vision.caltech.edu/visipedia/CUB-200-2011.html

Yuheng-Li avatar Dec 20 '21 16:12 Yuheng-Li