Audio Classification on OpenMIC
86.7mAPBEATs iter3+
Evaluation results
| Method | Links | |
|---|---|---|
| BEATs iter3+Training data=AS, Learning type=Supervised, Evaluation protocol=Linear evaluation2025.02 | 86.7 | |
| PaSSTTraining data=AS, Learning type=Supervised, Evaluation protocol=Linear evaluation2025.02 | 86.5 | |
| HTS-ATTraining data=AS, Learning type=Supervised, Evaluation protocol=Linear evaluation2025.02 | 86.4 | |
| MATPAC++Role=Teacher, Size=86M2026.04 | 85.6 | |
| MATPACTraining data=AS, nr,epoch=20, Learning type=SSL, Evaluation protocol=Linear evaluation2025.02 | 85.4 | |
| MATPACTraining data=AS, nr,epoch=10, Learning type=SSL, Evaluation protocol=Linear evaluation2025.02 | 85.3 | |
| MATPAC w/o ClassificationTraining data=AS, Learning type=SSL, Evaluation protocol=Linear evaluation2025.02 | 85.1 | |
| M2Dratio=0.7, Training data=AS, Learning type=SSL, Evaluation protocol=Linear evaluation2025.02 | 84.8 | |
| S-SONDO (DyMN)Teacher=MATPAC++, Size=8.7M2026.04 | 84.8 | |
| M2DRole=Teacher, Size=86M2026.04 | 84.8 | |
| S-SONDO (MobileNetV3)Teacher=MATPAC++, Size=2.9M2026.04 | 84.7 | |
| MobileNetV3Teacher=None (Supervised), Size=2.9M2026.04 | 84.5 | |
| DyMNTeacher=None (Supervised), Size=8.7M2026.04 | 84.3 | |
| ATST-ClipTraining data=AS, Learning type=SSL, Evaluation protocol=Linear evaluation2025.02 | 84.2 | |
| ATST-FrameTraining data=AS, Learning type=SSL, Evaluation protocol=Linear evaluation2025.02 | 83.1 | |
| S-SONDO (MobileNetV3)Teacher=M2D, Size=2.9M2026.04 | 83.1 | |
| S-SONDO (DyMN)Teacher=M2D, Size=8.7M2026.04 | 83.1 | |
| BEATS iter3Training data=AS, Learning type=SSL, Evaluation protocol=Linear evaluation2025.02 | 82.7 | |
| S-SONDO (ERes2Net)Teacher=MATPAC++, Size=1.4M2026.04 | 82.6 | |
| S-SONDO (ERes2Net)Teacher=M2D, Size=1.4M2026.04 | 81.5 | |
| MAE-ASTTraining data=AS+LS, Learning type=SSL, Evaluation protocol=Linear evaluation2025.02 | 79.4 | |
| ERes2NetTeacher=None (Supervised), Size=1.4M2026.04 | 75 |