[Paper Review] BEIT: BERT Pre-Training of Image Transformers

발표자: 정용기

1. 논문제목
BEIT: BERT Pre-Training of Image Transformers

2. Overview
Visual Tokenizer, Masked Image Modeling 을 Vision Transformer 에 적용하여 Self-supervised learning 방식을 제안한 연구

3. Reference
BEIT: BERT Pre-Training of Image Transformers
Neural Discrete Representation Learning (VQ-VAE)
Zero-Shot Text-to-Image Generation (DALL-E)
[Paper Review] data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language

Видео [Paper Review] BEIT: BERT Pre-Training of Image Transformers канала 고려대학교 산업경영공학부 DSBA 연구실