Audio Classification on ESC
95.5Top-1 AccuracySLAP_Wavcaps
Evaluation Results
| Method | Links | |
|---|---|---|
| SLAP_WavcapsZero-shot=true, training_data=WavCaps2026.01 | 95.5 | |
| MGA-CLAPZero-shot=true2026.01 | 94.9 | |
| WavCapsZero-shot=true2026.01 | 94.8 | |
| M2D2Zero-shot=true2026.01 | 94.3 | |
| MS-CLAPZero-shot=true2026.01 | 93.9 | |
| GLAPZero-shot=true2026.01 | 88.8 | |
| SLAPZero-shot=true2026.01 | 88.6 | |
| AudioSetCapsZero-shot=true2026.01 | 88 | |
| MambAdapterAdapter Configuration=Houlsby, Parameters (M)=0.112026.06 | 87.55 | |
| FFTParameters (M)=852026.06 | 87.48 | |
| ConformerAdapter Configuration=Pfeiffer, Parameters (M)=0.272026.06 | 87.28 | |
| MambAdapterAdapter Configuration=Pfeiffer, Parameters (M)=0.062026.06 | 87.28 | |
| BottleneckAdapter Configuration=Houlsby, Parameters (M)=0.492026.06 | 87.15 | |
| DPTParameters (M)=0.272026.06 | 86.52 | |
| LoRAParameters (M)=0.262026.06 | 86.45 | |
| BottleneckAdapter Configuration=Pfeiffer, Parameters (M)=0.252026.06 | 86.31 | |
| BitFitParameters (M)=0.122026.06 | 86.05 | |
| ConformerAdapter Configuration=Houlsby, Parameters (M)=0.542026.06 | 84.98 | |
| Pref-TParameters (M)=0.262026.06 | 82.93 | |
| AudioCLIPEmergent=false, Supervision=Uses audio and text supervision2023.05 | 68.6 | |
| IMAGEBINDEmergent=true, Supervision=No audio and text supervision2023.05 | 66.9 |