Field Definition of "psg_cls_advanced.json"

[Elfsong]

Hi,

Where can I find the definition of each field in the file "psg_cls_advanced.json"? For example:

• What do "category_id", "area", and "gqa_category_id" stand for in the "segments_info" section?
• How does the "relations" section work? There are multiple groups of "relations", so which objects does this depict the relations between?
• In the "annotations" part, what is "bbox_mode"? Is the definition of "category_id" the same as in the "segments_info" section?

In the "psg_cls_basic.json", do "relations" fields include ALL relationships between objects in an image?

An introduction to this kind of terminology and how these things work together will be very helpful to fresh CVers.

Best, Mingzhe

[Jingkang50]

Thank you for your questions. You could read this to know more details.

What do "category_id", "area", and "gqa_category_id" stand for in the "segments_info" section?

category_id means the class id. area means the number of pixels for the mask. You can ignore GQA id as it maps class id to another dataset.

How does the "relations" section work? There are multiple groups of "relations", so which objects does this depict the relations between? In the "annotations" part, what is "bbox_mode"? Is the definition of "category_id" the same as in the "segments_info" section?

I believe you could understand it after reading this

Thanks!

[Elfsong]

Thanks @Jingkang50!