BriefGPT.xyz
Sep, 2019
用于图像和文本分类的监督多模式双向转换器
Supervised Multimodal Bitransformers for Classifying Images and Text
HTML
PDF
Douwe Kiela, Suvrat Bhooshan, Hamed Firooz, Davide Testuggine
TL;DR
该研究介绍了一种监督式多模态双向Transformer模型，该模型融合了文本编码器和图像编码器的信息，并在各种多模态分类基准任务上获得了最先进的性能。
Abstract
self-supervised
bidirectional transformer models such as
bert
have led to dramatic improvements in a wide variety of textual
classification
→