Environmental Sound Classification on ESC-50
91.8Top-1 AccSOTA [87]
Evaluation Results
| Method | Links | |
|---|---|---|
| SOTA [87]2023.11 | 91.8 | |
| Hybrid BYOL-S/CvT2022.06 | 83.8 | |
| Hybrid BYOL-S/CvTalpha:beta ratio=1:12022.06 | 83.8 | |
| BYOL-Swindow size (s)=0.52022.06 | 83.3 | |
| Hybrid BYOL-S/CvTalpha:beta ratio=2:12022.06 | 83.1 | |
| Hybrid BYOL-S/Default2022.06 | 82.4 | |
| Hybrid BYOL-S/CvTalpha:beta ratio=4:12022.06 | 82.4 | |
| Hybrid BYOL-S/CvTalpha:beta ratio=3:22022.06 | 82.3 | |
| BYOL-S2022.06 | 81.9 | |
| BYOL-Swindow size (s)=0.952022.06 | 81.4 | |
| BYOL-Swindow size (s)=22022.06 | 81.3 | |
| BYOL-Swindow size (s)=1.4252022.06 | 80.3 | |
| BYOL-S++2022.06 | 80 | |
| BYOL-Sencoder=CvT2022.06 | 79.9 | |
| Hybrid BYOL-S/CvTalpha:beta ratio=2:32022.06 | 79.6 | |
| BYOL-A2022.06 | 78.9 | |
| Hybrid BYOL-S/CvTalpha:beta ratio=1:22022.06 | 78.4 | |
| BYOL-S/CvT + OS2022.06 | 76.9 | |
| ViT-LENS_Lanchor=I+T2023.11 | 75.9 | |
| BYOL-Sencoder=CLSTM2022.06 | 73.9 | |
| Hybrid BYOL-S/CvTalpha:beta ratio=1:42022.06 | 72.5 | |
| BYOL-Sencoder=Resnetish-342022.06 | 71.5 | |
| ViT-LENS_Lanchor=I2023.11 | 69.2 | |
| AudioCLIPanchor=I+T2023.11 | 68.4 | |
| openSMILE (OS)2022.06 | 68.2 | |
| ImageBind-Hanchor=I2023.11 | 66.9 | |
| wav2vec22022.06 | 59.2 | |
| CREPE2022.06 | 29.4 |