Text Recognition on SVT (Word Accuracy)
96.9Word AccuracyMaskOCR (ViT-S)
Evaluation Results
| Method | Links | |
|---|---|---|
| MaskOCR (ViT-S)VP (Visual Pre-training)=true, LP (Language Pre-training)=true, AD (Annotated Data)=real, #Params=31M2022.06 | 96.9 | |
| MaskOCR (ViT-B)VP (Visual Pre-training)=true, LP (Language Pre-training)=true, AD (Annotated Data)=real, #Params=97M2022.06 | 96.9 | |
| DiG (ViT-B)VP (Visual Pre-training)=true, LP (Language Pre-training)=false, AD (Annotated Data)=real, #Params=52M2022.06 | 96.5 | |
| DiG (ViT-S)VP (Visual Pre-training)=true, LP (Language Pre-training)=false, AD (Annotated Data)=real, #Params=36M2022.06 | 96.1 | |
| MaskOCR (ViT-B)VP (Visual Pre-training)=true, LP (Language Pre-training)=true, AD (Annotated Data)=synth, #Params=97M2022.06 | 94.9 | |
| MaskOCR (ViT-B)VP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth, #Params=97M2022.06 | 94.7 | |
| PerSecVP (Visual Pre-training)=true, LP (Language Pre-training)=false, AD (Annotated Data)=synth2022.06 | 94.6 | |
| DiG (ViT-B)VP (Visual Pre-training)=true, LP (Language Pre-training)=false, AD (Annotated Data)=synth, #Params=52M2022.06 | 94.6 | |
| ConCLRVP (Visual Pre-training)=false, LP (Language Pre-training)=true, AD (Annotated Data)=synth, #Params=37M2022.06 | 94.3 | |
| MaskOCR (ViT-S)VP (Visual Pre-training)=true, LP (Language Pre-training)=true, AD (Annotated Data)=synth, #Params=31M2022.06 | 94 | |
| MaskOCR (ViT-S)VP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth, #Params=31M2022.06 | 93.7 | |
| ABINetVP (Visual Pre-training)=false, LP (Language Pre-training)=true, AD (Annotated Data)=synth, #Params=37M2022.06 | 93.5 | |
| DiG (ViT-S)VP (Visual Pre-training)=true, LP (Language Pre-training)=false, AD (Annotated Data)=synth, #Params=36M2022.06 | 93.4 | |
| TrOCRVP (Visual Pre-training)=true, LP (Language Pre-training)=true, AD (Annotated Data)=synth, #Params=558M2022.06 | 93.2 | |
| VisionLanVP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth, #Params=33M2022.06 | 91.7 | |
| I2C2WVP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth2022.06 | 91.7 | |
| SRNVP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth, #Params=55M2022.06 | 91.5 | |
| PIMNetVP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth2022.06 | 91.2 | |
| ABINetVP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth, #Params=24M2022.06 | 90.4 | |
| TextScannerVP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth2022.06 | 90.1 | |
| SEEDVP (Visual Pre-training)=false, LP (Language Pre-training)=true, AD (Annotated Data)=synth2022.06 | 89.6 | |
| ASTERVP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth2022.06 | 89.5 |