Audio Classification On Fsd50K
評価指標
mAP
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 | mAP | Paper Title | Repository |
|---|---|---|---|
| PaSST-N-S | 64.2 | Efficient Training of Audio Transformers with Patchout | |
| MN | 65.6 | Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models | |
| Temporal Knowledge Distillation for On-device Audio Classification | 54.8 | Temporal Knowledge Distillation for On-device Audio Classification | - |
| LHGNN | - | LHGNN: Local-Higher Order Graph Neural Networks For Audio Classification and Tagging | - |
| Large 6-Layer Transformer with Pooling | 53.7 | Audio Transformers | - |
| ONE-PEACE | 69.7 | ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities | |
| DyMN-L | 65.5 | Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models | |
| PaSST-S | 65.55 | Efficient Training of Audio Transformers with Patchout | |
| PSLA | 56.71 | PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation |
0 of 9 row(s) selected.