[Paper] CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features (Image Classification) | by Sik-Ho Tsang | Nov, 2020

CutMix: Patches are cut and pasted among training image

In this story, CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features (CutMix), by NAVER Corp., LINE Plus Corp., and Yonsei University, is shortly presented. In this paper:

  • Patches are cut and pasted among training images where the ground truth labels are also mixed proportionally to the area of the patches.
  • By making efficient use of training pixels and retaining the regularization effect of regional dropout, CutMix consistently outperforms the state-of-the-art augmentation strategies.

This is a paper in 2019 ICCV with over 190 citations. (Sik-Ho Tsang @ Medium)

Share:

More Posts

Send Us A Message