HyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAI

Few Shot Audio Classification On Nsynth

Metrics

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

Results

Performance results of various models on this benchmark

Model Name
Top-1 Accuracy(5-Way-1-Shot)
Paper TitleRepository
MAML (CRNN)93.85 +- 0.24MetaAudio: A Few-Shot Audio Classification Benchmark
SimpleShot CL2N Classifier (AST pre-trained w/ ImageNet - No fine-tune)66.68 +- 0.41MetaAudio: A Few-Shot Audio Classification Benchmark
MT-SLVR (SimCLR + MLAP) w/ Parallel Adapters (FSD50K, RN18)71.81±0.39MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations
SimCLR (FSD50K, RN18)66.44±0.40MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations
Meta-Baseline (CRNN)90.74 +- 0.25MetaAudio: A Few-Shot Audio Classification Benchmark
SimpleShot CL2N Classifier (AST ImageNet & AudioSet - No fine-tune)63.78 +- 0.42MetaAudio: A Few-Shot Audio Classification Benchmark
SimpleShot CL2N (CRNN)90.04 +- 0.27MetaAudio: A Few-Shot Audio Classification Benchmark
Meta-Curvature (CRNN)96.47 +-0.19MetaAudio: A Few-Shot Audio Classification Benchmark
Multi-Label Augmentation Prediction (FSD50K, RN18)62.52±0.36MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations
Prototypical Networks (CRNN)95.23 +- 0.19MetaAudio: A Few-Shot Audio Classification Benchmark
0 of 10 row(s) selected.