Image Captioning on Widget Captioning
136.7CIDErPix2Struct-Large
Evaluation Results
| Method | Links | |
|---|---|---|
| Pix2Struct-LargeInput type=Pixel-only, Scale=Large2022.10 | 136.7 | |
| Pix2Struct-BaseInput type=Pixel-only, Scale=Base2022.10 | 133.1 | |
| DonutInput type=Pixel-only2022.10 | 127.4 |