Scene Text Recognition on IC13 857 (test)
98.1AccuracyABINet++ (LV)
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| ABINet++ (LV)Labeled Datasets=MJ+ST+Real, Vision Model Scale=LV2022.11 | 98.1 | — | — | |
| ABINet++‡ (LV)Labeled Datasets=MJ+ST, Unlabeled Datasets=Uber-Text, Vision Model Scale=LV, Training Strategy=ensemble self-training2022.11 | 97.7 | — | — | |
| ABINet++ (LV)Labeled Datasets=MJ+ST, Vision Model Scale=LV2022.11 | 97.4 | — | 33.9 | |
| ABINet++† (LV)Labeled Datasets=MJ+ST, Unlabeled Datasets=Uber-Text, Vision Model Scale=LV, Training Strategy=self-training2022.11 | 97.3 | — | — | |
| ABINet++ (SV)Labeled Datasets=MJ+ST, Vision Model Scale=SV2022.11 | 96.8 | — | 31.6 | |
| SRN* (LV)Labeled Datasets=MJ+ST, Reproduced=true, Vision Model Scale=LV2022.11 | 96.8 | — | 26.9 | |
| PIMNet Qiao et al.Year=2021, Labeled Datasets=MJ+ST+Real2022.11 | 96.6 | — | — | |
| STN-CSTRTraining Data=MJ+ST, Annotations=word, STN=true2021.02 | 96.3 | — | — | |
| SRN* (SV)Labeled Datasets=MJ+ST, Reproduced=true, Vision Model Scale=SV2022.11 | 96.3 | — | 24.2 | |
| VisionLan Wang et al.Year=2021, Labeled Datasets=MJ+ST2022.11 | 95.7 | — | 11.5 | |
| SRN Yu et al.Year=2020, Labeled Datasets=MJ+ST2022.11 | 95.5 | — | 46.2 | |
| CSTRTraining Data=MJ+ST, Annotations=word, STN=false2021.02 | 95.3 | — | — | |
| PIMNet Qiao et al.Year=2021, Labeled Datasets=MJ+ST2022.11 | 95.2 | — | 19.1 | |
| SSFLSetting=Reported results, Year=2018, Train data=MJ2019.04 | 94 | — | — | |
| Our best modelSetting=Our experiment, Train data=MJ+ST2019.04 | 93.6 | — | — | |
| Baek et al.Training Data=MJ+ST, Annotations=word2021.02 | 93.6 | — | — | |
| STAR-NetSetting=Our experiment, Year=2016, Train data=MJ+ST2019.04 | 92.8 | — | — | |
| RARESetting=Our experiment, Year=2016, Train data=MJ+ST2019.04 | 92.6 | — | — | |
| CRNNSetting=Our experiment, Year=2015, Train data=MJ+ST2019.04 | 91.1 | — | — | |
| GRCNNSetting=Our experiment, Year=2017, Train data=MJ+ST2019.04 | 90.9 | — | — | |
| RosettaSetting=Our experiment, Year=2018, Train data=MJ+ST2019.04 | 90.9 | — | — | |
| Char-NetSetting=Reported results, Year=2018, Train data=MJ2019.04 | 90.8 | — | — | |
| R2AMSetting=Our experiment, Year=2016, Train data=MJ+ST2019.04 | 90.2 | — | — | |
| R2AMSetting=Reported results, Year=2016, Train data=MJ2019.04 | 90 | — | — | |
| STAR-NetSetting=Reported results, Year=2016, Train data=MJ+PRI2019.04 | 89.1 | — | — | |
| RARESetting=Reported results, Year=2016, Train data=MJ2019.04 | 88.6 | — | — | |
| CRNNSetting=Reported results, Year=2015, Train data=MJ2019.04 | 86.7 | — | — | |
| ABINet2021.09 | — | 97.4 | — | |
| Diaz2021.09 | — | 96 | — | |
| MaskOCRBackbone=ViT-B2021.09 | — | 98.1 | — | |
| MaskOCRBackbone=ViT-L2021.09 | — | 97.8 | — | |
| PARSeq2021.09 | — | 97 | — | |
| PARSeq-BTrain Data=REBU-Syn2023.12 | — | 99.07 | — | |
| PARSeq-HParameters=0.6B, Train Data=REBU-Syn2023.12 | — | 99.11 | — | |
| PARSeq-LTrain Data=REBU-Syn2023.12 | — | 99.3 | — | |
| PARSeq-SParameters=22M, Train Data=REBU-Syn2023.12 | — | 98.72 | — | |
| PlugNet2021.09 | — | 95 | — | |
| PREN2D2021.09 | — | 96.4 | — | |
| SRN2021.09 | — | 95.5 | — | |
| STN-CSTR2021.09 | — | 96.3 | — | |
| TrOCRBackbone=TrOCR-Base, Training Data=Synthetic2021.09 | — | 97.3 | — | |
| TrOCRBackbone=TrOCR-Large, Training Data=Synthetic2021.09 | — | 98.3 | — | |
| TrOCRBackbone=TrOCR-Base, Training Data=Synthetic + Benchmark2021.09 | — | 98.4 | — | |
| TrOCRBackbone=TrOCR-Large, Training Data=Synthetic + Benchmark2021.09 | — | 98.4 | — | |
| VisionLAN2021.09 | — | 95.7 | — | |
| VITSTR-B2021.09 | — | 93.2 | — |