Scene Text Recognition on TextOCR + Open Images (100% labeled samples)
95.6AccuracyMaskOCR
Evaluation results
| Method | Links | |
|---|---|---|
| MaskOCRPre-training=Visual-Language, Backbone=ViT-S, Number of parameters=31M2022.06 | 95.6 | |
| MaskOCRPre-training=Visual, Backbone=ViT-S, Number of parameters=31M2022.06 | 95.3 | |
| MaskOCRPre-training=Scratch, Backbone=ViT-S, Number of parameters=31M2022.06 | 95.2 | |
| DiGPre-training=Visual, Backbone=ViT-S, Number of parameters=36M2022.06 | 94.6 | |
| DiGPre-training=Scratch, Backbone=ViT-S, Number of parameters=36M2022.06 | 91.4 | |
| CRNNPre-training=Scratch, Backbone=CRNN, Number of parameters=25M2022.06 | 89.4 |