Image Classification on ImageNet ESC-19 (val)
69.3Accuracy (1-shot)Image-Audio Linear
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Image-Audio LinearModality=Image + Audio2023.01 | 69.3 | 76.7 | 83.2 | |
| Image-Only LinearModality=Image-Only2023.01 | 68 | 75.7 | 83.1 |
| Method | Links | |||
|---|---|---|---|---|
| Image-Audio LinearModality=Image + Audio2023.01 | 69.3 | 76.7 | 83.2 | |
| Image-Only LinearModality=Image-Only2023.01 | 68 | 75.7 | 83.1 |