Sound Event Detection on DESED (val)
0.024PSDS-1 ScoreBYOL-A-V2-40ms
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| BYOL-A-V2-40msEvaluation Protocol=Linear Evaluation, tau (ms)=40, learning rate=0.012023.06 | 0.024 | 0.181 | — | |
| SSAST-FRAME-20msEvaluation Protocol=Linear Evaluation, tau (ms)=20, learning rate=0.12023.06 | 0.028 | 0.166 | — | |
| BYOL-A-V2-40msEvaluation Protocol=Finetuning, tau (ms)=40, learning rate=0.012023.06 | 0.03 | 0.219 | — | |
| MAE-AST-FRAME-20msEvaluation Protocol=Linear Evaluation, tau (ms)=20, learning rate=0.12023.06 | 0.031 | 0.234 | — | |
| SSAST-FRAME-20msEvaluation Protocol=Finetuning, tau (ms)=20, learning rate=0.052023.06 | 0.046 | 0.235 | — | |
| MAE-AST-FRAME-40msEvaluation Protocol=Linear Evaluation, tau (ms)=40, learning rate=0.12023.06 | 0.081 | 0.293 | — | |
| SSAST-FRAME-40msEvaluation Protocol=Linear Evaluation, tau (ms)=40, learning rate=0.12023.06 | 0.096 | 0.266 | — | |
| ATST-ClipEvaluation Protocol=Linear Evaluation, tau (ms)=40, learning rate=0.12023.06 | 0.115 | 0.293 | — | |
| MAE-AST-FRAME-20msEvaluation Protocol=Finetuning, tau (ms)=20, learning rate=0.052023.06 | 0.123 | 0.346 | — | |
| SSAST-FRAME-40msEvaluation Protocol=Finetuning, tau (ms)=40, learning rate=0.12023.06 | 0.132 | 0.325 | — | |
| BEATSiter3Evaluation Protocol=Linear Evaluation, tau (ms)=160, learning rate=0.12023.06 | 0.177 | 0.358 | — | |
| SSAST-PATCHEvaluation Protocol=Linear Evaluation, tau (ms)=160, learning rate=0.12023.06 | 0.179 | 0.315 | — | |
| Audio-MAE (local)Evaluation Protocol=Linear Evaluation, tau (ms)=160, learning rate=0.12023.06 | 0.218 | 0.401 | — | |
| ATST-ClipEvaluation Protocol=Finetuning, tau (ms)=40, learning rate=0.052023.06 | 0.223 | 0.422 | — | |
| MAE-AST-PATCHEvaluation Protocol=Linear Evaluation, tau (ms)=160, learning rate=0.12023.06 | 0.225 | 0.442 | — | |
| M2DEvaluation Protocol=Linear Evaluation, tau (ms)=160, learning rate=0.12023.06 | 0.234 | 0.438 | — | |
| MAE-AST-FRAME-40msEvaluation Protocol=Finetuning, tau (ms)=40, learning rate=0.12023.06 | 0.235 | 0.418 | — | |
| SSAST-PATCHEvaluation Protocol=Finetuning, tau (ms)=160, learning rate=0.12023.06 | 0.236 | 0.459 | — | |
| Audio-MAE (local)Evaluation Protocol=Finetuning, tau (ms)=160, learning rate=0.12023.06 | 0.254 | 0.509 | — | |
| ATST-F2CEvaluation Protocol=Finetuning, tau (ms)=40, learning rate=0.12023.06 | 0.259 | 0.445 | — | |
| M2DEvaluation Protocol=Finetuning, tau (ms)=160, learning rate=0.12023.06 | 0.267 | 0.5 | — | |
| MAE-AST-PATCHEvaluation Protocol=Finetuning, tau (ms)=160, learning rate=0.052023.06 | 0.281 | 0.573 | — | |
| BEATSiter3Evaluation Protocol=Finetuning, tau (ms)=160, learning rate=0.12023.06 | 0.282 | 0.584 | — | |
| ATST-FrameEvaluation Protocol=Linear Evaluation, tau (ms)=40, learning rate=0.12023.06 | 0.304 | 0.507 | — | |
| ATST-C2FEvaluation Protocol=Finetuning, tau (ms)=40, learning rate=0.12023.06 | 0.357 | 0.607 | — | |
| ATST-FrameEvaluation Protocol=Finetuning, tau (ms)=40, learning rate=0.012023.06 | 0.361 | 0.581 | — | |
| FDY-CRNNPost-Processing=cw-mf, SSL Method=MT2024.06 | 0.451 | — | — | |
| DFD-CRNNPost-Processing=cw-mf, SSL Method=MT2024.06 | 0.455 | — | 0.465 | |
| MDFD-CRNNPost-Processing=mf, SSL Method=MT2024.06 | 0.455 | — | 0.468 | |
| MFD-CRNNPost-Processing=cw-mf, SSL Method=MT2024.06 | 0.461 | — | — | |
| MDFD-CRNNPost-Processing=cw-mf, SSL Method=MT2024.06 | 0.461 | — | 0.474 | |
| MFD-CRNNPost-Processing=cw-mf, SSL Method=CMT2024.06 | 0.47 | — | — | |
| MDFD-CRNNPost-Processing=cSEBBs, SSL Method=MT2024.06 | — | — | 0.485 |