I was reading some papers about semantic and instance segmentation (e.g. YOLACT) and often encountered the term 'prototype learning'. Could you please explain this concept?

  • $\begingroup$ A prototype is a dictionary image used as a mask to factor an image into component parts. When this has been done, the image has been spelt or learned in terms of the odd looking shapes in the dictionary. $\endgroup$ – Carl May 19 at 16:19
  • $\begingroup$ Do you have an example or some reference with more details on this topic? $\endgroup$ – Javiator May 19 at 18:50
  • $\begingroup$ The example that you linked to should suffice, if it does not look up other dictionary image reconstruction methods. $\endgroup$ – Carl May 19 at 19:30

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.