File size: 374 Bytes
5fa1a76 |
1 2 3 4 |
It is a series of bidirectional transformer encoders (one for the vision modality, one for the language modality, and then one to fuse both modalities) pretrained using a combination of masked language modeling, visual-language text alignment, ROI-feature regression, masked visual-attribute modeling, masked visual-object modeling, and visual-question answering objectives. |