paper-with-me

Batchboost

2000년 도입 · 논문 1편에서 사용

Batchboost is a variation on MixUp that instead of mixing just two images, mixes many images together.

출처: batchboost: regularization for stabilizing training with resistance to underfitting & overfitting

소개 논문: batchboost: regularization for stabilizing training with resistance to underfitting & overfitting

Image Data Augmentation · Computer Vision