I see so many papers claim to have an algorithm that beats 'human-level performance' for semantic segmentation tasks, but I can't find any papers reporting on what the human-level performance actually is. An analysis of the similarity between segmentations drawn by multiple different human experts would be good. Could someone point me towards a paper that reports on something like that?


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.