Object Dropout

2000년 도입 · 논문 1편에서 사용

Object Dropout is a technique that perturbs object features in an image for noisy student training. It performs at par with standard data augmentation techniques while being significantly faster than the latter to implement.

출처: Perturb, Predict & Paraphrase: Semi-Supervised Learning using Noisy Student for Image Captioning

소개 논문: Perturb, Predict & Paraphrase: Semi-Supervised Learning using Noisy Student for Image Captioning