Audio Classification on ImageNet ESC-27 (val)
35Accuracy (1-shot)Audio-Image Linear
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Audio-Image LinearModality=Audio + Image2023.01 | 35 | 43.5 | 48.5 | |
| Audio-Only LinearModality=Audio-Only2023.01 | 28.2 | 39 | 47.1 |
| Method | Links | |||
|---|---|---|---|---|
| Audio-Image LinearModality=Audio + Image2023.01 | 35 | 43.5 | 48.5 | |
| Audio-Only LinearModality=Audio-Only2023.01 | 28.2 | 39 | 47.1 |