Audio Classification On Balanced Audio Set
評価指標
Mean AP
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | Mean AP | Paper Title | Repository |
|---|---|---|---|
| EquiAV | 42.4 | EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning | - |
| BEATs | 38.9 | BEATs: Audio Pre-Training with Acoustic Tokenizers | - |
| SSAST-PATCH | 31.0 | SSAST: Self-Supervised Audio Spectrogram Transformer | - |
| EAT | 40.3 | EAT: Self-Supervised Pre-Training with Efficient Audio Transformer | - |
| Base (ours) | 37.4 | ATST: Audio Representation Learning with Teacher-Student Transformer | - |
| Conformer | 27.6 | Conformer-Based Self-Supervised Learning for Non-Speech Audio Tasks | - |
| SSLAM | 40.9 | SSLAM: Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic Soundscapes | |
| SSAST-FRAME | 29.2 | SSAST: Self-Supervised Audio Spectrogram Transformer | - |
0 of 8 row(s) selected.