List your company

Audio Tagging on AudioSet (test)

50mAPSOTA
24.93631.44337.9544.457Jun 3, 2021Mar 31, 2022Jan 27, 2023Nov 24, 2023Sep 21, 2024Jul 19, 2025May 17, 2026

Evaluation results

MethodLinks
SOTAtype=non-CLAP-based2026.0150
EAT-CSUCategory=Proposed, # Parameters=111 M2026.0549.61
EAT-CHCategory=Proposed, # Parameters=111 M2026.0549.02
M2D2type=CLAP-based, protocol=linear classification layer fine-tuning2026.0149
Efficient Audio Transformer (EAT)Category=Self-Supervised Learning, # Parameters=88 M2026.0548.6
AST (Ensemble-M)e2e=false, Params=526.6 * 10^62021.0648.5
BEATsCategory=Self-Supervised Learning, # Parameters=90 M2026.0548
SLAPtype=CLAP-based, protocol=linear classification layer fine-tuning2026.0147.8
Audio Masked Autoencoder (AudioMAE)Category=Self-Supervised Learning, # Parameters=86 M2026.0547.3
Masked Spectrogram Prediction (MaskSpec)Category=Self-Supervised Learning, # Parameters=86 M2026.0547.1
ASTe2e=false, Params=88.1 * 10^62021.0645.9
Audio Spectrogram Transformer (AST)Category=Supervised Learning, # Parameters=86 M2026.0545.9
ERANN-1-6e2e=false, Params=54.5 * 10^62021.0645
ERANN-2-5e2e=false, Params=38.2 * 10^62021.0644.6
Multimodal Bottleneck Transformer (MBT)Category=Supervised Learning, # Parameters=86 M2026.0544.3
BLATtype=CLAP-based, protocol=linear classification layer fine-tuning2026.0144
Wavegram-Logmel-CNNe2e=false, Params=81.1 * 10^62021.0643.9
CNN14e2e=false, Params=80.7 * 10^62021.0643.1
Pretrained Audio Neural Networks (PANNs)Category=Supervised Learning, # Parameters=81 M2026.0543.1
Conformer-based Self-Supervised LearningCategory=Self-Supervised Learning, # Parameters=88 M2026.0541.1
Wavegram-CNNe2e=true, Params=81.0 * 10^62021.0638.9
AemNet-DW (WM=2)e2e=true, Params=3.0 * 10^62021.0634
AemNet-DW (WM=1)e2e=true, Params=1.2 * 10^62021.0632.9
ESResNeXte2e=false, Params=31.1 * 10^62021.0628.2
AudioCLIPCategory=Supervised Learning, # Parameters=93 M2026.0525.9