Table 5 Semi-supervised learning error rates (%) on ESC-10, UBS8K, and GSC
From: Comparison of semi-supervised deep learning algorithms for audio classification
Dataset | ESC-10 | UBS8K | GSC | |||
|---|---|---|---|---|---|---|
Labeled fraction | 10% | 100% | 10% | 100% | 10% | 100% |
Supervised | 32.00 ± 6.17 | 8.00 ±5.06 | 33.80 ±4.82 | 23.29 ±5.80 | 10.01 | 4.94 |
Best supervised | 22.67 ± 3.46 | 4.67 ±1.39 | 23.75 ±4.73 | 17.96 ±3.64 | 6.58 | 2.98 |
MT | 28.28 ± 5.28 | - | 32.80 ±4.21 | - | 8.51 | - |
MT+mixup | 27.81 ± 2.25 | - | 32.00 ±5.80 | - | 8.50 | - |
DCT | 25.16 ± 4.42 | - | 27.85 ±4.29 | - | 6.22 | - |
DCT+mixup | 23.75 ± 2.36 | - | 25.77 ±4.73 | - | 5.63 | - |
MM-mixup | 17.33 ± 3.84 | - | 20.42 ±4.88 | - | 4.49 | - |
MM | 15.33 ± 5.58 | - | 18.02 ±4.00 | - | 3.25 | - |
RMM-mixup | 32.50 ±11.71 | - | 38.23 ±6.15 | - | 5.15 | - |
RMM | 12.00 ±5.55 | - | 28.41 ±6.54 | - | 3.54 | - |
FM | 13.33 ± 2.89 | - | 21.44 ±4.16 | - | 4.44 | - |
FM+mixup | 14.67 ± 7.21 | - | 18.27 ±3.80 | - | 3.31 | - |