Startseite Neuigkeiten Neueste Forschungsarbeiten Tutorials Datensätze Wiki SOTA LLM-Modelle GPU-Rangliste Veranstaltungen

Deutsch

Few Shot Audio Classification On Voxceleb1

Metriken

Top-1 Accuracy(5-Way-1-Shot)

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	Top-1 Accuracy(5-Way-1-Shot)	Paper Title	Repository
Meta-Curvature (CRNN)	63.85 +- 0.44	MetaAudio: A Few-Shot Audio Classification Benchmark
SimpleShot CL2N (AST ImageNet - No fine-tune)	28.09 +- 0.37	MetaAudio: A Few-Shot Audio Classification Benchmark
Prototypical Networks (CRNN)	59.64 +- 0.44	MetaAudio: A Few-Shot Audio Classification Benchmark
Meta-Baseline (CRNN)	55.54 +- 0.42	MetaAudio: A Few-Shot Audio Classification Benchmark
MAML (CRNN)	60.89 +- 0.45	MetaAudio: A Few-Shot Audio Classification Benchmark
SimCLR (FSD50K, RN18)	31.18±0.37	MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations
SimpleShot CL2N (CRNN)	48.50 +- 0.42	MetaAudio: A Few-Shot Audio Classification Benchmark
MT-SLVR (SimCLR + MLAP) w/ Parallel Adapters (FSD50K, RN18)	33.58±0.39	MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations
Multi-Label Augmentation Prediction (FSD50K, RN18)	21.68±0.40	MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations
SimpleShot CL2N (AST ImageNet & AudioSet- No fine-tune)	28.79 +- 0.38	MetaAudio: A Few-Shot Audio Classification Benchmark

0 of 10 row(s) selected.