BriefGPT.xyz
Apr, 2022
视觉语言预训练模型：一项调查
Vision-and-Language Pretrained Models: A Survey
HTML
PDF
Siqu Long, Feiqi Cao, Soyeon Caren Han, Haiqing Yang
TL;DR
本文主要介绍了预训练模型在计算机视觉和自然语言处理中所取得的巨大成功，着重介绍了视觉语言预训练模型(VLPM)的重要进展及其结构、预训练和微调策略，并提出了未来三个方向的研究建议。
Abstract
pretrained models
have produced great success in both
computer vision
(CV) and
natural language processing
(NLP). This progress leads to l
→