I tried to fine tune Faster RCNN to realize object detection task with bounding boxes where I shall recognize face, eyes and mouth on image. However Faster RCNN seems to fail to recognize objects when they contain another one(face contains nose). I tried the same task on faces only and it worked good.

Is it a general behavior? How can I explain that? Is there a trick to get over it?

  • $\begingroup$ what do you get when face contains nose, for example? $\endgroup$
    – Nikos M.
    Mar 28, 2021 at 19:14
  • $\begingroup$ either no box for face or a completely wrong prediction for face $\endgroup$
    – nprime496
    Mar 28, 2021 at 20:08


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.