Audio Classification on Average over 11 datasets
82.05Base AccuracyCOCOOP
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| COCOOPSetting=Few-Shot2026.06 | 82.05 | — | — | 50.44 | |
| COCOOP + ZEBRASetting=Few-Shot, Framework=ZEBRA2026.06 | 81.75 | — | — | 59.5 | |
| COOP + ZEBRASetting=Few-Shot, Framework=ZEBRA2026.06 | 80.17 | — | — | 59.37 | |
| COOPSetting=Few-Shot2026.06 | 79.82 | — | — | 48.04 | |
| CoCoOpShots=16, Evaluation Protocol=Base-to-new generalization2026.01 | 69.13 | 36.83 | 46.26 | — | |
| CoCoOp + SEPTShots=16, Evaluation Protocol=Base-to-new generalization2026.01 | 68.63 | 42.59 | 50.65 | — | |
| CoOpShots=16, Evaluation Protocol=Base-to-new generalization2026.01 | 65 | 34.09 | 42.83 | — | |
| CoOplearning_mode=16-shot learning, protocol=base-to-new generalization2026.01 | 65 | 34.09 | 42.83 | — | |
| DePT + SEPTShots=16, Evaluation Protocol=Base-to-new generalization2026.01 | 64.57 | 41.63 | 49.06 | — | |
| CoOp + SEPTShots=16, Evaluation Protocol=Base-to-new generalization2026.01 | 64.36 | 42.98 | 49.7 | — | |
| DePTShots=16, Evaluation Protocol=Base-to-new generalization2026.01 | 63.86 | 39.91 | 46.79 | — | |
| KgCoOp†learning_mode=16-shot learning, protocol=base-to-new generalization, prompt_templates=100 hand-crafted ensemble2026.01 | 59.02 | 38.76 | 44.76 | — | |
| KgCoOp + SEPTShots=16, Evaluation Protocol=Base-to-new generalization2026.01 | 58.92 | 45.28 | 49.79 | — | |
| KgCoOp† + SEPTlearning_mode=16-shot learning, protocol=base-to-new generalization, prompt_templates=100 hand-crafted ensemble2026.01 | 58.34 | 40.52 | 46.31 | — | |
| ZERO SHOTSetting=Zero-Shot2026.06 | 53.53 | — | — | 55.18 | |
| PengiShots=16, Evaluation Protocol=Base-to-new generalization2026.01 | 40.68 | 38.21 | 38.46 | — | |
| KgCoOpShots=16, Evaluation Protocol=Base-to-new generalization2026.01 | 37.99 | 37.42 | 36.39 | — | |
| KgCoOplearning_mode=16-shot learning, protocol=base-to-new generalization, prompt_templates=single2026.01 | 37.99 | 37.42 | 36.39 | — |