Acoustic Classification on Multi-Dataset Average (DeepShip, VTUAD, ESC-50, TUT)
6.98Average GainStudent + CNN14
Evaluation results
| Method | Links | |
|---|---|---|
| Student + CNN14Teacher Model=CNN14, # Parameters (Student vs. Teacher)=12.3K vs. 79.7M, Adaptation Strategy=Full teacher fine-tuning2025.01 | 6.98 | |
| Student + MobileNetV1Teacher Model=MobileNetV1, # Parameters (Student vs. Teacher)=12.3K vs. 4.3M, Adaptation Strategy=Full teacher fine-tuning2025.01 | 6.79 | |
| Student + ResNet38Teacher Model=ResNet38, # Parameters (Student vs. Teacher)=12.3K vs. 72.7M, Adaptation Strategy=Full teacher fine-tuning2025.01 | 6.52 | |
| Student + HuBERTTeacher Model=HuBERT, # Parameters (Student vs. Teacher)=12.3K vs. 95.7M, Adaptation Strategy=Full teacher fine-tuning2025.01 | 6 | |
| Student + WhisperTeacher Model=Whisper, # Parameters (Student vs. Teacher)=12.3K vs. 74.0M, Adaptation Strategy=Full teacher fine-tuning2025.01 | 5.7 | |
| Student + Wav2Vec 2.0Teacher Model=Wav2Vec 2.0, # Parameters (Student vs. Teacher)=12.3K vs. 95.0M, Adaptation Strategy=Full teacher fine-tuning2025.01 | 5.25 |