Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks. (arXiv:2208.10442v2 [cs.CV] UPDATED)

A big convergence of language, vision, and multimodal pretraining is
emerging. In this work, we introduce a general-purpose multimodal foundation
model BEiT-3, which achieves state-of-the-art transfer performance on both
vision and vision-language tasks. Specifically, we advance the big convergence
from three aspects: backbone architecture, pretraining task, and model scaling
up. We introduce Multiway Transformers for general-purpose modeling, where the
modular architecture enables both deep fusion and modality-specific encoding.
Based on the shared backbone, we perform masked "language" modeling on images …

arxiv foreign language image language vision