Audio Classification on CREMA-D (test)
45.06AccuracyMUKA
Evaluation results
| Method | Links | |
|---|---|---|
| MUKATraining Approach=Training-free, Shots=16, Backbone=PENGI2026.02 | 45.06 | |
| Linear ProbingTraining Approach=Training-based, Shots=16, Backbone=PENGI2026.02 | 40.18 | |
| PaLMTraining Approach=Training-based, Shots=16, Backbone=PENGI2026.02 | 34.59 | |
| CoOpTraining Approach=Training-based, Shots=16, Backbone=PENGI2026.02 | 33.62 | |
| CoCoOpTraining Approach=Training-based, Shots=16, Backbone=PENGI2026.02 | 30.18 | |
| Audio Flamingozero-shot=true2024.02 | 26.5 | |
| Zero-ShotTraining Approach=Training-free, Shots=0, Backbone=PENGI2026.02 | 23.1 | |
| Treff-AdapterTraining Approach=Training-free, Shots=16, Backbone=PENGI2026.02 | 20.46 | |
| Deshmukh et al., 2023zero-shot=true2024.02 | 18.5 |