| MetaAudio: A Few-Shot Audio Classification Benchmark | ✓ Link | 61.34 +- 0.46 | Meta-Curvature (CRNN) | 2022-04-05 |
| MetaAudio: A Few-Shot Audio Classification Benchmark | ✓ Link | 57.66 +- 0.43 | SimpleShot Cl2N (CRNN) | 2022-04-05 |
| MetaAudio: A Few-Shot Audio Classification Benchmark | ✓ Link | 57.28 +- 0.41 | Meta-Baseline (CRNN) | 2022-04-05 |
| MetaAudio: A Few-Shot Audio Classification Benchmark | ✓ Link | 56.26 +- 0.45 | MAML (CRNN) | 2022-04-05 |
| MetaAudio: A Few-Shot Audio Classification Benchmark | ✓ Link | 56.11 +- 0.46 | Prototypical Networks (CRNN) | 2022-04-05 |
| MetaAudio: A Few-Shot Audio Classification Benchmark | ✓ Link | 36.41 +- 0.42 | SimpleShot CL2N (AST ImageNet & AudioSet- No fine-tune) | 2022-04-05 |
| MetaAudio: A Few-Shot Audio Classification Benchmark | ✓ Link | 33.04 +- 0.41 | SimpleShot CL2N (AST ImageNet - No fine-tune) | 2022-04-05 |
| MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations | ✓ Link | 30.93±0.38 | SimCLR (FSD50K, RN18) | 2023-05-29 |
| MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations | ✓ Link | 29.49±0.38 | MT-SLVR (SimCLR + MLAP) w/ Parallel Adapters (FSD50K, RN18) | 2023-05-29 |
| MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations | ✓ Link | 21.04±0.35 | Multi-Label Augmentation Prediction (FSD50K, RN18) | 2023-05-29 |