List your company

Audio Classification on AudioSet

49.6mAPAbsolute SOTA
-1.245611.954725.15538.3553Jun 29, 2020Jun 22, 2021Jun 15, 2022Jun 8, 2023May 31, 2024May 24, 2025May 18, 2026

Evaluation results

MethodLinks
Absolute SOTAAnchor Modality=–2026.0449.6
ASTModel Architecture=Pure Attention, Ensemble Config=Ensemble-M2021.0448.5
ASTModel Architecture=Pure Attention, Ensemble Config=Ensemble-S2021.0447.5
PSLAModel Architecture=CNN+Attention, Ensemble Config=Ensemble-M2021.0447.4
AV-MAEPretraining=SSL AS-2M, Training set=AS-500K2022.1246.6
PSLAModel Architecture=CNN+Attention, Ensemble Config=Ensemble-S2021.0446.4
ASTModel Architecture=Pure Attention, Ensemble Config=Single2021.0445.9
PSLAModel Architecture=CNN+Attention, Ensemble Config=Single2021.0444.4
SupervisedProtocol=MLP2020.0643.9
PANNsModel Architecture=CNN+Attention2021.0443.9
MBTPretraining=Im21K, Training set=AS-500K2022.1241.5
PerceiverPretraining=None, Training set=AS-2M2022.1238.4
Fayek et al.Pretraining=Im1K, Training set=AS-2M2022.1238.4
GBlendPretraining=Im1K, Training set=AS-2M2022.1232.4
BaselineModel Architecture=CNN+MLP2021.0431.4
MMV FACBackbone=TSM-50x2, Train data=AS+HT2020.0630.9
VA onlyBackbone=S3D-G, Train data=AS+HT2020.0630.6
MMV FACBackbone=TSM-50, Train data=AS+HT2020.0630.6
MMV FACBackbone=S3D-G, Train data=AS+HT2020.0630.3
LanguageBind2026.0530
VA onlyBackbone=R(2+1)D-18, Train data=AS2020.0629.7
VA onlyBackbone=S3D-G, Train data=AS2020.0629.7
CodeBind-VL2026.0529.2
AA+AV CCBackbone=RN-50 (23.5M), Train data=AS, Modality=VA2020.0628.5
AudioCLIPAnchor Modality=–2026.0428.4
EmergentBridgeAnchor Modality=Text2026.0428.1
LanguageBindAnchor Modality=Text2026.0427.7
ViT-LENS_Lanchor=I+T2023.1126.7
AudioCLIPanchor=I+T2023.1125.9
EmergentBridgeAnchor Modality=Image2026.0425.4
OmniBind2026.0525.1
UNIALIGN2026.0523.8
ViT-LENS_Lanchor=I2023.1123.1
CLAPAnchor Modality=–2026.0423.1
SAM-780Mr=256, Conn.=(a), Experiment=E52025.0921.1
SAM-2.7Br=256, Conn.=(a), Experiment=E62025.0921.1
SAM-2.7Br=256, Conn.=(b), Ablation=4.2, Experiment=E142025.0921.1
CodeBind-IB2026.0521.1
SAM-2.7Br=256, Conn.=(a), Ablation=4.1, Experiment=E92025.0921
SAM-2.7Br=8, Conn.=(a), Experiment=E32025.0920.8
SAM-2.7Br=256, Conn.=(a), Ablation=4.3, Experiment=E182025.0920.8
SAM-2.7Br=256, Conn.=(c), Ablation=4.2, Experiment=E152025.0920.7
SAM-780Mr=256, Conn.=(a), Ablation=4.3, Experiment=E172025.0920.7
SAM-780Mr=256, Conn.=(c), Ablation=4.2, Experiment=E132025.0920.5
SAM-780Mr=256, Conn.=(a), Ablation=4.1, Experiment=E82025.0920.4
SAM-780Mr=8, Conn.=(a), Experiment=E22025.0920.3
SAM-780Mr=256, Conn.=(b), Ablation=4.2, Experiment=E122025.0920
SAM-130Mr=256, Conn.=(a), Experiment=E42025.0919.9
SAM-130Mr=8, Conn.=(a), Experiment=E12025.0919.7
FreeBind2026.0519.7
ssLALM-2.8Br=8, Conn.=Linear2025.0919.4
GAMA-7Br=8, Conn.=QFormer2025.0919.2
SAM-130Mr=256, Conn.=(c), Ablation=4.2, Experiment=E112025.0919.1
SAM-130Mr=256, Conn.=(a), Ablation=4.3, Experiment=E162025.0919
SAM-130Mr=256, Conn.=(b), Ablation=4.2, Experiment=E102025.0918.8
LTU-7Br=8, Conn.=Linear2025.0918.7
SAM-130Mr=256, Conn.=(a), Ablation=4.1, Experiment=E72025.0918.2
ImageBind-Hanchor=I2023.1117.6
ImageBindAnchor Modality=Image2026.0417.6
WAV2CLIPAnchor Modality=–2026.040.71