Image as a Foreign Language: BEiT Pretraining for Vision and Vision-Language Tasks
- Wenhui Wang ,
- Hangbo Bao ,
- Li Dong ,
- Johan Bjorck ,
- Zhiliang Peng ,
- Qiang Liu ,
- Kriti Aggarwal ,
- Owais Khan Mohammed ,
- Saksham Singhal ,
- Subhojit Som ,
- Furu Wei
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
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 excellent 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 use 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 (Imglish), texts (English), and image-text pairs (“parallel sentences”) in a unified manner. Experimental results show that BEiT-3 obtains remarkable performance on object detection (COCO), semantic segmentation (ADE20K), image classification (ImageNet), visual reasoning (NLVR2), visual question answering (VQAv2), image captioning (COCO), and cross-modal retrieval (Flickr30K, COCO).