Few Shot Audio Classification On Watkins
評価指標
Top-1 Accuracy(5-Way-1-Shot)
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 | Top-1 Accuracy(5-Way-1-Shot) | Paper Title | Repository |
|---|---|---|---|
| Multi-Label Augmentation Prediction (FSD50K, RN18) | 28.88±0.39 | MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations | |
| MT-SLVR (SimCLR + MLAP) w/ Parallel Adapters (FSD50K, RN18) | 59.49±0.42 | MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations | |
| SimpleShot CL2N (AST ImageNet & AudioSet- No fine-tune) | 51.81 ± 0.42 | MetaAudio: A Few-Shot Audio Classification Benchmark | |
| SimCLR (FSD50K, RN18) | 52.91±0.41 | MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations | |
| SimpleShot CL2N (AST ImageNet - No fine-tune) | 55.40 ± 0.42 | MetaAudio: A Few-Shot Audio Classification Benchmark |
0 of 5 row(s) selected.