CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features

2019 inproceedings yun2019cutmix ○ Not yet verified

Authors

Sangdoo Yun, Dongyoon Han, Seong Joon Oh, Sanghyuk Chun, Junsuk Choe, Youngjoon Yoo

Venue

ICCV 2019

Abstract

Combines cutting and mixing: patches from one image replace regions in another, with labels mixed proportionally. Improves over Cutout by using cut pixels constructively rather than zeroing them out.

BibTeX

Local Entry

@inproceedings{yun2019cutmix,
  title = {CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features},
  author = {Sangdoo Yun and Dongyoon Han and Seong Joon Oh and Sanghyuk Chun and Junsuk Choe and Youngjoon Yoo},
  year = {2019},
  booktitle = {ICCV 2019},
  url = {https://arxiv.org/abs/1905.04899},
  abstract = {Combines cutting and mixing: patches from one image replace regions in another, with labels mixed proportionally. Improves over Cutout by using cut pixels constructively rather than zeroing them out.}
}

From OPENALEX

@inproceedings{yun2019cutmix,
  title = {CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features},
  author = {Sangdoo Yun and Dongyoon Han and Sanghyuk Chun and Seong Joon Oh and Youngjoon Yoo and Junsuk Choe},
  year = {2019},
  doi = {10.1109/iccv.2019.00612}
}