Sound Event Classification on Urban Sound
82.21Top-1 AccuracyPALM + ASPL*
Evaluation Results
| Method | Links | |
|---|---|---|
| PALM + ASPL*Shots=16, Audio Encoder=CLAP-HTSAT, Text Encoder=CLIP (PENGI)2026.06 | 82.21 | |
| PALM + ASPLShots=16, Audio Encoder=CLAP-HTSAT, Text Encoder=CLIP (PENGI)2026.06 | 81.73 | |
| PALMShots=16, Audio Encoder=CLAP-HTSAT, Text Encoder=CLIP (PENGI)2026.06 | 80.97 | |
| CoCoOp + ASPL*Shots=16, Audio Encoder=CLAP-HTSAT, Text Encoder=CLIP (PENGI)2026.06 | 79.72 | |
| CoCoOp + ASPLShots=16, Audio Encoder=CLAP-HTSAT, Text Encoder=CLIP (PENGI)2026.06 | 79.65 | |
| CoCoOpShots=16, Audio Encoder=CLAP-HTSAT, Text Encoder=CLIP (PENGI)2026.06 | 78.67 | |
| CoOp + ASPL*Shots=16, Audio Encoder=CLAP-HTSAT, Text Encoder=CLIP (PENGI)2026.06 | 77.4 | |
| CoOp + ASPLShots=16, Audio Encoder=CLAP-HTSAT, Text Encoder=CLIP (PENGI)2026.06 | 76.3 | |
| CoOpShots=16, Audio Encoder=CLAP-HTSAT, Text Encoder=CLIP (PENGI)2026.06 | 76.1 |