Multi-label Classification on PTB-XL (test)
0.913Macro AUCER-JEPA
Evaluation results
| Method | Links | ||
|---|---|---|---|
| ER-JEPAPretrain dataset=Shao+CODE15, Pretrain Records=180 K2026.07 | 0.913 | — | |
| ER-JEPAPretrain dataset=Shao+CODE15, Pretrain Records=180 K, Downstream trials=102026.07 | 0.913 | — | |
| ECG-JEPAPretrain dataset=Shao+CODE15, Pretrain Records=180 K2026.07 | 0.912 | — | |
| 1D-JEPAPretrain dataset=Shao+CODE15, Pretrain Records=180 K, Number of pretrained encoders=52026.07 | 0.901 | — | |
| KEDPretrain dataset=MIMIC-IV-ECG, Pretrain Records=800 K2026.07 | 0.885 | — | |
| ST-MEMPretrain dataset=Shao+CODE15, Pretrain Records=180 K2026.07 | 0.882 | — | |
| ECG-FMPretrain dataset=UHN [10], Pretrain Records=622 K2026.07 | 0.878 | — | |
| SimCLRPretrain dataset=Shao+CODE15, Pretrain Records=180 K2026.07 | 0.875 | — | |
| ECG-FMEvaluation Protocol=Linear evaluation2024.10 | — | 87.8 | |
| ECG-JEPAmbEvaluation Protocol=Linear evaluation, Masking Strategy=Multi-block masking2024.10 | — | 91.2 | |
| ECG-JEPArbEvaluation Protocol=Linear evaluation, Masking Strategy=Random masking2024.10 | — | 90.6 | |
| KEDEvaluation Protocol=Linear evaluation2024.10 | — | 88.5 | |
| SimCLREvaluation Protocol=Linear evaluation2024.10 | — | 87.5 | |
| ST-MEMEvaluation Protocol=Linear evaluation2024.10 | — | 88.2 |