In this paper[1] there is a section where it is mentioned that “The most commonly used L1 loss will have different scales for small and large objects even if their relative errors are similar”.

I don’t understand this statement. Can anybody explain?

[1]: End-to-End Object Detection with Transformers

  • $\begingroup$ We expect references to fulfill the minimal scholarly requirements and be as robust over time as possible. Please take some time to improve your post in this regard. We have collected some advice here. This will hopefully help others with a similar question about the same paper find this page via search. Thank you! $\endgroup$
    – D.W.
    Jul 16, 2021 at 16:53


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.