Scene Text Recognition on IC15 1811 (test)
89.2AccuracyABINet++ (LV)
Evaluation results
| Method | Links | ||
|---|---|---|---|
| ABINet++ (LV)Labeled Datasets=MJ+ST+Real, Vision Model Scale=LV2022.11 | 89.2 | — | |
| PIMNet Qiao et al.Year=2021, Labeled Datasets=MJ+ST+Real2022.11 | 88.7 | — | |
| ABINet++† (LV)Labeled Datasets=MJ+ST, Unlabeled Datasets=Uber-Text, Vision Model Scale=LV, Training Strategy=self-training2022.11 | 87.4 | — | |
| ABINet++‡ (LV)Labeled Datasets=MJ+ST, Unlabeled Datasets=Uber-Text, Vision Model Scale=LV, Training Strategy=ensemble self-training2022.11 | 86.9 | — | |
| STN-CSTRTraining Data=MJ+ST, Annotations=word, STN=true2021.02 | 86.1 | — | |
| ABINet++ (LV)Labeled Datasets=MJ+ST, Vision Model Scale=LV2022.11 | 86 | 33.9 | |
| CSTRTraining Data=MJ+ST, Annotations=word, STN=false2021.02 | 85.6 | — | |
| SRN* (LV)Labeled Datasets=MJ+ST, Reproduced=true, Vision Model Scale=LV2022.11 | 84.2 | 26.9 | |
| ABINet++ (SV)Labeled Datasets=MJ+ST, Vision Model Scale=SV2022.11 | 84 | 31.6 | |
| VisionLan Wang et al.Year=2021, Labeled Datasets=MJ+ST2022.11 | 83.7 | 11.5 | |
| PIMNet Qiao et al.Year=2021, Labeled Datasets=MJ+ST2022.11 | 83.5 | 19.1 | |
| Textscanner Wan et al.Year=2020, Labeled Datasets=MJ+ST+Real2022.11 | 83.5 | — | |
| SRNTraining Data=MJ+ST, Annotations=word2021.02 | 82.7 | — | |
| SRN Yu et al.Year=2020, Labeled Datasets=MJ+ST2022.11 | 82.7 | 46.2 | |
| SRN* (SV)Labeled Datasets=MJ+ST, Reproduced=true, Vision Model Scale=SV2022.11 | 82.6 | 24.2 | |
| SEED Qiao et al.Year=2020, Labeled Datasets=MJ+ST2022.11 | 80 | 53.3 | |
| GTC Hu et al.Year=2020, Labeled Datasets=MJ+ST+Real2022.11 | 79.5 | — | |
| Textscanner Wan et al.Year=2020, Labeled Datasets=MJ+ST2022.11 | 79.4 | — | |
| Our best modelSetting=Our experiment, Train data=MJ+ST2019.04 | 77.6 | — | |
| Baek et al.Training Data=MJ+ST, Annotations=word2021.02 | 77.6 | — | |
| STAR-NetSetting=Our experiment, Year=2016, Train data=MJ+ST2019.04 | 76.1 | — | |
| RARESetting=Our experiment, Year=2016, Train data=MJ+ST2019.04 | 74.5 | — | |
| DANTraining Data=MJ+ST, Annotations=word2021.02 | 74.5 | — | |
| EPSetting=Reported results, Year=2018, Train data=MJ+ST2019.04 | 73.9 | — | |
| GRCNNSetting=Our experiment, Year=2017, Train data=MJ+ST2019.04 | 71.4 | — | |
| RosettaSetting=Our experiment, Year=2018, Train data=MJ+ST2019.04 | 71.2 | — | |
| FANSetting=Reported results, Year=2017, Train data=MJ+ST+C2019.04 | 70.6 | — | |
| FANTraining Data=MJ+ST, Annotations=word2021.02 | 70.6 | — | |
| CRNNSetting=Our experiment, Year=2015, Train data=MJ+ST2019.04 | 69.4 | — | |
| R2AMSetting=Our experiment, Year=2016, Train data=MJ+ST2019.04 | 68.9 | — |