List your company

Text Recognition on SVTP

94.9Word AccuracyMaskOCR (ViT-S)
77.84482.27286.791.128Jun 1, 2022

Evaluation results

MethodLinks
MaskOCR (ViT-S)VP (Visual Pre-training)=true, LP (Language Pre-training)=true, AD (Annotated Data)=real, #Params=31M2022.0694.9
MaskOCR (ViT-B)VP (Visual Pre-training)=true, LP (Language Pre-training)=true, AD (Annotated Data)=real, #Params=97M2022.0694.6
DiG (ViT-B)VP (Visual Pre-training)=true, LP (Language Pre-training)=false, AD (Annotated Data)=real, #Params=52M2022.0692.9
DiG (ViT-S)VP (Visual Pre-training)=true, LP (Language Pre-training)=false, AD (Annotated Data)=real, #Params=36M2022.0691.6
DiG (ViT-B)VP (Visual Pre-training)=true, LP (Language Pre-training)=false, AD (Annotated Data)=synth, #Params=52M2022.0691
TrOCRVP (Visual Pre-training)=true, LP (Language Pre-training)=true, AD (Annotated Data)=synth, #Params=558M2022.0691
MaskOCR (ViT-S)VP (Visual Pre-training)=true, LP (Language Pre-training)=true, AD (Annotated Data)=synth, #Params=31M2022.0690.2
DiG (ViT-S)VP (Visual Pre-training)=true, LP (Language Pre-training)=false, AD (Annotated Data)=synth, #Params=36M2022.0690.1
MaskOCR (ViT-B)VP (Visual Pre-training)=true, LP (Language Pre-training)=true, AD (Annotated Data)=synth, #Params=97M2022.0689.8
PerSecVP (Visual Pre-training)=true, LP (Language Pre-training)=false, AD (Annotated Data)=synth2022.0689.5
MaskOCR (ViT-B)VP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth, #Params=97M2022.0689.3
ABINetVP (Visual Pre-training)=false, LP (Language Pre-training)=true, AD (Annotated Data)=synth, #Params=37M2022.0689.3
ConCLRVP (Visual Pre-training)=false, LP (Language Pre-training)=true, AD (Annotated Data)=synth, #Params=37M2022.0689.3
MaskOCR (ViT-S)VP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth, #Params=31M2022.0689
VisionLanVP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth, #Params=33M2022.0686
SRNVP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth, #Params=55M2022.0685.1
TextScannerVP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth2022.0684.3
PIMNetVP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth2022.0684.3
ABINetVP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth, #Params=24M2022.0684.2
I2C2WVP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth2022.0683.1
SEEDVP (Visual Pre-training)=false, LP (Language Pre-training)=true, AD (Annotated Data)=synth2022.0681.4
ASTERVP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth2022.0678.5