Audio Tagging on AudioSet Strong
21.6mAPMTC (AudioSet)
Evaluation Results
| Method | Links | |
|---|---|---|
| MTC (AudioSet)Label=Tag, Evaluation Protocol=linear probing, Pooling Strategy=mean-pooling2026.03 | 21.6 | |
| Multi-Task (Ours)Label=Tag*, Caption*, Evaluation Protocol=linear probing, Pooling Strategy=mean-pooling2026.03 | 14 | |
| PAR (Ours-UTS)Label=Tag Sequence*, Evaluation Protocol=linear probing, Pooling Strategy=mean-pooling2026.03 | 12.1 | |
| MTC (Ours-UTS)Label=Tag*, Evaluation Protocol=linear probing, Pooling Strategy=mean-pooling2026.03 | 11.3 | |
| Contrastive-scratch (Ours)Label=Caption*, Evaluation Protocol=linear probing, Pooling Strategy=mean-pooling2026.03 | 10.5 | |
| Contrastive-scratchLabel=Caption, Evaluation Protocol=linear probing, Pooling Strategy=mean-pooling2026.03 | 9.5 | |
| Captioning-scratch (Ours)Label=Caption*, Evaluation Protocol=linear probing, Pooling Strategy=mean-pooling2026.03 | 8.7 | |
| Captioning-scratchLabel=Caption, Evaluation Protocol=linear probing, Pooling Strategy=mean-pooling2026.03 | 7.7 | |
| BEATsLabel=-, Evaluation Protocol=linear probing, Pooling Strategy=mean-pooling2026.03 | 3.4 |