Search code examples
deep-learningcomputer-visionpytorchobject-detection

Classes in Coco dataset

I have been checking out this detr repository and the total number of classes are 100, but 10 of these are empty string as shown here.
Is there any particular reason behind this?

Solution

  • Basically, the COCO dataset was described in a paper before its release (you can find it here). At this point, the authors gave a list of the 91 types of objects that would be in the dataset.

    But when the 2014 and 2017 datasets were released, it turned out that you could find only 80 of these objects in the annotations.

    The list you have is the original list of objects (as described in the paper) but with every object that does not appear in the 2014 and 2017 replaced by the empty string "".

    My guess is that the sole purpose of keeping these "phantom" objects is to keep consistency with object ids that may have been fixed someday in the past.

    If you want to learn more about it, you can look at this blog entry.