List your company

Text Recognition on SVT (Word Accuracy)

96.9Word AccuracyMaskOCR (ViT-S)
89.20491.20293.295.198Jun 1, 2022

Evaluation results

MethodLinks
MaskOCR (ViT-S)VP (Visual Pre-training)=true, LP (Language Pre-training)=true, AD (Annotated Data)=real, #Params=31M2022.0696.9
MaskOCR (ViT-B)VP (Visual Pre-training)=true, LP (Language Pre-training)=true, AD (Annotated Data)=real, #Params=97M2022.0696.9
DiG (ViT-B)VP (Visual Pre-training)=true, LP (Language Pre-training)=false, AD (Annotated Data)=real, #Params=52M2022.0696.5
DiG (ViT-S)VP (Visual Pre-training)=true, LP (Language Pre-training)=false, AD (Annotated Data)=real, #Params=36M2022.0696.1
MaskOCR (ViT-B)VP (Visual Pre-training)=true, LP (Language Pre-training)=true, AD (Annotated Data)=synth, #Params=97M2022.0694.9
MaskOCR (ViT-B)VP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth, #Params=97M2022.0694.7
PerSecVP (Visual Pre-training)=true, LP (Language Pre-training)=false, AD (Annotated Data)=synth2022.0694.6
DiG (ViT-B)VP (Visual Pre-training)=true, LP (Language Pre-training)=false, AD (Annotated Data)=synth, #Params=52M2022.0694.6
ConCLRVP (Visual Pre-training)=false, LP (Language Pre-training)=true, AD (Annotated Data)=synth, #Params=37M2022.0694.3
MaskOCR (ViT-S)VP (Visual Pre-training)=true, LP (Language Pre-training)=true, AD (Annotated Data)=synth, #Params=31M2022.0694
MaskOCR (ViT-S)VP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth, #Params=31M2022.0693.7
ABINetVP (Visual Pre-training)=false, LP (Language Pre-training)=true, AD (Annotated Data)=synth, #Params=37M2022.0693.5
DiG (ViT-S)VP (Visual Pre-training)=true, LP (Language Pre-training)=false, AD (Annotated Data)=synth, #Params=36M2022.0693.4
TrOCRVP (Visual Pre-training)=true, LP (Language Pre-training)=true, AD (Annotated Data)=synth, #Params=558M2022.0693.2
VisionLanVP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth, #Params=33M2022.0691.7
I2C2WVP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth2022.0691.7
SRNVP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth, #Params=55M2022.0691.5
PIMNetVP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth2022.0691.2
ABINetVP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth, #Params=24M2022.0690.4
TextScannerVP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth2022.0690.1
SEEDVP (Visual Pre-training)=false, LP (Language Pre-training)=true, AD (Annotated Data)=synth2022.0689.6
ASTERVP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth2022.0689.5