List your company
ResearchFormerly WizWand

Music Genre Classification on GTZAN (test)

96AccuracyLAION-CLAP
24.926443.378261.8380.2818Jun 4, 2024Sep 26, 2024Jan 19, 2025May 13, 2025Sep 5, 2025Dec 28, 2025Apr 22, 2026
Updated 6mo ago

Evaluation results

MethodLinks
LAION-CLAPzero-shot=true2024.0696
Explicit Dropout (K)Dropout on Attention Sequence=Explicit (K), Dropout on FF network=Explicit, Dropout ratio=0.2, Model Architecture=2-layer Transformer encoder2026.0485.78
Explicit Dropout (Q)Dropout on Attention Sequence=Explicit (Q), Dropout on FF network=Explicit, Dropout ratio=0.2, Model Architecture=2-layer Transformer encoder2026.0485.68
Arora et al. (Q)Dropout on Attention Sequence=(Q) Arora et al. [1], Dropout on FF network=Explicit, Dropout ratio=0.2, Model Architecture=2-layer Transformer encoder2026.0485.31
Arora et al. (V)Dropout on Attention Sequence=(V) Arora et al. [1], Dropout on FF network=Explicit, Dropout ratio=0.2, Model Architecture=2-layer Transformer encoder2026.0485.16
Explicit Dropout (None)Dropout on Attention Sequence=None, Dropout on FF network=Explicit, Dropout ratio=0.2, Model Architecture=2-layer Transformer encoder2026.0485.16
None (Implicit)Dropout on Attention Sequence=None, Dropout on FF network=Implicit, Dropout ratio=0.2, Model Architecture=2-layer Transformer encoder2026.0485
Explicit Dropout (V)Dropout on Attention Sequence=Explicit (V), Dropout on FF network=Explicit, Dropout ratio=0.2, Model Architecture=2-layer Transformer encoder2026.0485
Explicit Dropout (AV)Dropout on Attention Sequence=Explicit (AV), Dropout on FF network=Explicit, Dropout ratio=0.2, Model Architecture=2-layer Transformer encoder2026.0485
DropAttentionDropout on Attention Sequence=DropAttention, Dropout on FF network=Implicit, Dropout ratio=0.2, Model Architecture=2-layer Transformer encoder2026.0484.84
DropKeyDropout on Attention Sequence=DropKey, Dropout on FF network=Implicit, Dropout ratio=0.2, Model Architecture=2-layer Transformer encoder2026.0484.84
Arora et al. (FF)Dropout on Attention Sequence=None, Dropout on FF network=Arora et al. [1], Dropout ratio=0.2, Model Architecture=2-layer Transformer encoder2026.0484.84
Arora et al. (K)Dropout on Attention Sequence=(K) Arora et al. [1], Dropout on FF network=Explicit, Dropout ratio=0.2, Model Architecture=2-layer Transformer encoder2026.0484.22
Proposed DNN classifierFeature Extractor=BYOL-A embeddings2026.0381.5
Proposed DNN classifierTraining Dataset=GTZAN2026.0381.5
Proposed DNN classifierFeature Extractor=VGGish embeddings2026.0379.5
Proposed DNN classifierTraining Dataset=GTZAN + FMA-Small2026.0378
Proposed DNN classifierFeature Extractor=PANNs embeddings2026.0377
M2D-CLAPmasking_ratio=0.7, zero-shot=true2024.0675.17
Niizumi et al.2026.0370.1
Niizumi et al.2026.0370.1
WavCapszero-shot=true2024.0652.1
JMLAzero-shot=false, note=Used test task data during training2024.0650.3
Proto-LCzero-shot=true2024.0647.24
AudioCLIPzero-shot=false, note=Used test task data during training2024.0645.52
Pengizero-shot=true2024.0628.97
Wav2CLIPzero-shot=true2024.0627.66