Audio Classification on ImageNet ESC-27
0.485AccuracyAudio-Image Linear
Evaluation results
| Method | Links | |
|---|---|---|
| Audio-Image LinearShots=4-shot, Audio Encoder=AudioCLIP (ES-ResNeXT), Modality=Cross-modal (Audio + Image)2023.01 | 0.485 | |
| Audio-Only LinearShots=4-shot, Audio Encoder=AudioCLIP (ES-ResNeXT)2023.01 | 0.471 | |
| Audio-Image LinearShots=2-shot, Audio Encoder=AudioCLIP (ES-ResNeXT), Modality=Cross-modal (Audio + Image)2023.01 | 0.435 | |
| Audio-Only LinearShots=2-shot, Audio Encoder=AudioCLIP (ES-ResNeXT)2023.01 | 0.39 | |
| Audio-Image LinearShots=1-shot, Audio Encoder=AudioCLIP (ES-ResNeXT), Modality=Cross-modal (Audio + Image)2023.01 | 0.35 | |
| Audio-Only LinearShots=1-shot, Audio Encoder=AudioCLIP (ES-ResNeXT)2023.01 | 0.282 |