0
$\begingroup$

In some research papers, people use random cropping with variable sizes and then they resize them to original size as a data augmentation technique saying that it helps boost results. Can someone help me understand why it boosts results when there's a risk that labels won't match the modified images?

$\endgroup$

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.