Scene Text Recognition on IIIT 3000 (test)
97.2AccuracyABINet++‡ (LV)
Evaluation results
| Method | Links | ||
|---|---|---|---|
| ABINet++‡ (LV)Labeled Datasets=MJ+ST, Unlabeled Datasets=Uber-Text, Vision Model Scale=LV, Training Strategy=ensemble self-training2022.11 | 97.2 | — | |
| ABINet++ (LV)Labeled Datasets=MJ+ST+Real, Vision Model Scale=LV2022.11 | 97.1 | — | |
| ABINet++† (LV)Labeled Datasets=MJ+ST, Unlabeled Datasets=Uber-Text, Vision Model Scale=LV, Training Strategy=self-training2022.11 | 96.8 | — | |
| PIMNet Qiao et al.Year=2021, Labeled Datasets=MJ+ST+Real2022.11 | 96.7 | — | |
| SRN* (LV)Labeled Datasets=MJ+ST, Reproduced=true, Vision Model Scale=LV2022.11 | 96.3 | 26.9 | |
| ABINet++ (LV)Labeled Datasets=MJ+ST, Vision Model Scale=LV2022.11 | 96.2 | 33.9 | |
| VisionLan Wang et al.Year=2021, Labeled Datasets=MJ+ST2022.11 | 95.8 | 11.5 | |
| GTC Hu et al.Year=2020, Labeled Datasets=MJ+ST+Real2022.11 | 95.8 | — | |
| Textscanner Wan et al.Year=2020, Labeled Datasets=MJ+ST+Real2022.11 | 95.7 | — | |
| ABINet++ (SV)Labeled Datasets=MJ+ST, Vision Model Scale=SV2022.11 | 95.4 | 31.6 | |
| RobustScanner Yue et al.Year=2020, Labeled Datasets=MJ+ST2022.11 | 95.3 | 36 | |
| PIMNet Qiao et al.Year=2021, Labeled Datasets=MJ+ST2022.11 | 95.2 | 19.1 | |
| Bhunia et al.Year=2021, Labeled Datasets=MJ+ST2022.11 | 95.2 | — | |
| SRN* (SV)Labeled Datasets=MJ+ST, Reproduced=true, Vision Model Scale=SV2022.11 | 95 | 24.2 | |
| SRN Yu et al.Year=2020, Labeled Datasets=MJ+ST2022.11 | 94.8 | 46.2 | |
| DAN Wang et al.Year=2020, Labeled Datasets=MJ+ST2022.11 | 94.3 | — | |
| Textscanner Wan et al.Year=2020, Labeled Datasets=MJ+ST2022.11 | 93.9 | — | |
| SEED Qiao et al.Year=2020, Labeled Datasets=MJ+ST2022.11 | 93.8 | 53.3 | |
| SSFLSetting=Reported results, Year=2018, Train data=MJ2019.04 | 89.4 | — | |
| EPSetting=Reported results, Year=2018, Train data=MJ+ST2019.04 | 88.3 | — | |
| Our best modelSetting=Our experiment, Train data=MJ+ST, Time (ms/image)=27.6, params=49.62019.04 | 87.9 | — | |
| FANSetting=Reported results, Year=2017, Train data=MJ+ST+C2019.04 | 87.4 | — | |
| AONSetting=Reported results, Year=2018, Train data=MJ+ST2019.04 | 87 | — | |
| STAR-NetSetting=Our experiment, Year=2016, Train data=MJ+ST, Time (ms/image)=10.9, params=48.72019.04 | 87 | — | |
| RARESetting=Our experiment, Year=2016, Train data=MJ+ST, Time (ms/image)=23.6, params=10.82019.04 | 86.2 | — | |
| RosettaSetting=Our experiment, Year=2018, Train data=MJ+ST, Time (ms/image)=4.7, params=44.32019.04 | 84.3 | — | |
| GRCNNSetting=Our experiment, Year=2017, Train data=MJ+ST, Time (ms/image)=10.7, params=4.62019.04 | 84.2 | — | |
| Char-NetSetting=Reported results, Year=2018, Train data=MJ2019.04 | 83.6 | — | |
| R2AMSetting=Our experiment, Year=2016, Train data=MJ+ST, Time (ms/image)=24.1, params=2.92019.04 | 83.4 | — | |
| STAR-NetSetting=Reported results, Year=2016, Train data=MJ+PRI2019.04 | 83.3 | — | |
| CRNNSetting=Our experiment, Year=2015, Train data=MJ+ST, Time (ms/image)=4.4, params=8.32019.04 | 82.9 | — | |
| RARESetting=Reported results, Year=2016, Train data=MJ, Time (ms/image)=<22019.04 | 81.9 | — | |
| GRCNNSetting=Reported results, Year=2017, Train data=MJ2019.04 | 80.8 | — | |
| R2AMSetting=Reported results, Year=2016, Train data=MJ, Time (ms/image)=2.22019.04 | 78.4 | — | |
| CRNNSetting=Reported results, Year=2015, Train data=MJ, Time (ms/image)=160, params=8.32019.04 | 78.2 | — |