I read in an article that object segmentation can do object detection better than object detection algorithms. I assume this is because there is more detailed information in the annotation images. I was wondering if this is true for object detection and multiclass image classification as well. If you just take the label and quantity of each label from object detection, does it perform better than multiclass image classification?

  • $\begingroup$ bump. jhgkhcxhngcc $\endgroup$
    – Skier
    Aug 13 '19 at 13:45

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.