List your company

Text Recognition on IIIT5K

98Word AccuracyMaskOCR (ViT-S)
90.7292.6194.596.39Jun 1, 2022

Evaluation results

MethodLinks
MaskOCR (ViT-S)VP (Visual Pre-training)=true, LP (Language Pre-training)=true, AD (Annotated Data)=real, #Params=31M2022.0698
MaskOCR (ViT-B)VP (Visual Pre-training)=true, LP (Language Pre-training)=true, AD (Annotated Data)=real, #Params=97M2022.0698
DiG (ViT-S)VP (Visual Pre-training)=true, LP (Language Pre-training)=false, AD (Annotated Data)=real, #Params=36M2022.0697.7
DiG (ViT-B)VP (Visual Pre-training)=true, LP (Language Pre-training)=false, AD (Annotated Data)=real, #Params=52M2022.0697.6
DiG (ViT-S)VP (Visual Pre-training)=true, LP (Language Pre-training)=false, AD (Annotated Data)=synth, #Params=36M2022.0696.7
DiG (ViT-B)VP (Visual Pre-training)=true, LP (Language Pre-training)=false, AD (Annotated Data)=synth, #Params=52M2022.0696.7
ConCLRVP (Visual Pre-training)=false, LP (Language Pre-training)=true, AD (Annotated Data)=synth, #Params=37M2022.0696.5
PerSecVP (Visual Pre-training)=true, LP (Language Pre-training)=false, AD (Annotated Data)=synth2022.0696.3
ABINetVP (Visual Pre-training)=false, LP (Language Pre-training)=true, AD (Annotated Data)=synth, #Params=37M2022.0696.2
VisionLanVP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth, #Params=33M2022.0695.8
MaskOCR (ViT-S)VP (Visual Pre-training)=true, LP (Language Pre-training)=true, AD (Annotated Data)=synth, #Params=31M2022.0695.8
MaskOCR (ViT-B)VP (Visual Pre-training)=true, LP (Language Pre-training)=true, AD (Annotated Data)=synth, #Params=97M2022.0695.8
MaskOCR (ViT-S)VP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth, #Params=31M2022.0695.4
MaskOCR (ViT-B)VP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth, #Params=97M2022.0695.3
PIMNetVP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth2022.0695.2
SRNVP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth, #Params=55M2022.0694.8
ABINetVP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth, #Params=24M2022.0694.6
I2C2WVP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth2022.0694.3
TextScannerVP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth2022.0693.9
SEEDVP (Visual Pre-training)=false, LP (Language Pre-training)=true, AD (Annotated Data)=synth2022.0693.8
ASTERVP (Visual Pre-training)=false, LP (Language Pre-training)=false, AD (Annotated Data)=synth2022.0693.4
TrOCRVP (Visual Pre-training)=true, LP (Language Pre-training)=true, AD (Annotated Data)=synth, #Params=558M2022.0691