Audio Classification on ImageNet ESC-19
51.6AccuracyAudio-Image Linear
Evaluation results
| Method | Links | |
|---|---|---|
| Audio-Image LinearShots=4-shot, Audio Encoder=AudioCLIP (ES-ResNeXT), Modality=Cross-modal (Audio + Image)2023.01 | 51.6 | |
| Audio-Only LinearShots=4-shot, Audio Encoder=AudioCLIP (ES-ResNeXT)2023.01 | 48.5 | |
| Audio-Image LinearShots=2-shot, Audio Encoder=AudioCLIP (ES-ResNeXT), Modality=Cross-modal (Audio + Image)2023.01 | 45.9 | |
| Audio-Only LinearShots=2-shot, Audio Encoder=AudioCLIP (ES-ResNeXT)2023.01 | 41.1 | |
| Audio-Image LinearShots=1-shot, Audio Encoder=AudioCLIP (ES-ResNeXT), Modality=Cross-modal (Audio + Image)2023.01 | 35.7 | |
| Audio-Only LinearShots=1-shot, Audio Encoder=AudioCLIP (ES-ResNeXT)2023.01 | 31.2 |