Audio Tagging on MagnaTagATune
40.7mAPMTC (AudioSet)
Evaluation Results
| Method | Links | |
|---|---|---|
| MTC (AudioSet)Label=Tag, Evaluation Protocol=linear probing, Pooling Strategy=mean-pooling2026.03 | 40.7 | |
| MERTLabel=-, Evaluation Protocol=linear probing, Pooling Strategy=mean-pooling2026.03 | 40.2 | |
| BEATsLabel=-, Evaluation Protocol=linear probing, Pooling Strategy=mean-pooling2026.03 | 40 | |
| Contrastive-scratch (Ours)Label=Caption*, Evaluation Protocol=linear probing, Pooling Strategy=mean-pooling2026.03 | 39.6 | |
| Multi-Task (Ours)Label=Tag*, Caption*, Evaluation Protocol=linear probing, Pooling Strategy=mean-pooling2026.03 | 39.6 | |
| Contrastive-scratchLabel=Caption, Evaluation Protocol=linear probing, Pooling Strategy=mean-pooling2026.03 | 38.4 | |
| PAR (Ours-UTS)Label=Tag Sequence*, Evaluation Protocol=linear probing, Pooling Strategy=mean-pooling2026.03 | 38.1 | |
| Captioning-scratchLabel=Caption, Evaluation Protocol=linear probing, Pooling Strategy=mean-pooling2026.03 | 37.8 | |
| Captioning-scratch (Ours)Label=Caption*, Evaluation Protocol=linear probing, Pooling Strategy=mean-pooling2026.03 | 37.7 | |
| MTC (Ours-UTS)Label=Tag*, Evaluation Protocol=linear probing, Pooling Strategy=mean-pooling2026.03 | 37.5 | |
| Wav2vec 2.0Label=-, Evaluation Protocol=linear probing, Pooling Strategy=mean-pooling2026.03 | 31.7 |