논문 함께 읽기/Data Augmentation (DA)
[DA] CutMix : Regularization Strategy to Train Strong Classifier with Localizable Features (ICCV2019)
안녕하세요. 오늘은 컴퓨터 비전 최고 학회 중 하나인 ICCV에 2019년에 억셉된 논문인 "CutMix : Regularization Strategy to Train Strong Classifier with Localizable Features"를 리뷰해보도록 하겠습니다. CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features Regional dropout strategies have been proposed to enhance the performance of convolutional neural network classifiers. They have proved to be effective for gu..
