List your company

Single-label environmental sound classification on ESC-50

96.9AccuracyMJEPA ViT-g + data scaling
73.579.57585.6591.725Jun 23, 2026

Evaluation results

MethodLinks
MJEPA ViT-g + data scalingEvaluation protocol=Frozen feature probing, Params=1B, Modality=A+V, Pre-train data=AS+VM2M2026.0696.9
MJEPA ViT-L + data scalingEvaluation protocol=Frozen feature probing, Params=300M, Modality=A+V, Pre-train data=AS+VM2M2026.0696.8
XKDEvaluation protocol=Full-model finetuning, Params=170M, Modality=A+V, Pre-train data=AS2026.0696.5
AJEPAEvaluation protocol=Full-model finetuning, Params=85M, Modality=A, Pre-train data=AS2026.0696.3
SSLAMEvaluation protocol=Full-model finetuning, Params=88M, Modality=A, Pre-train data=AS2026.0696.2
EquiAVEvaluation protocol=Full-model finetuning, Params=170M, Modality=A+V, Pre-train data=AS2026.0696
MJEPA ViT-LEvaluation protocol=Frozen feature probing, Params=300M, Modality=A+V, Pre-train data=AS2026.0695.2
MAViLEvaluation protocol=Full-model finetuning, Params=170M, Modality=A+V, Pre-train data=IN+AS2026.0694.4
XKDEvaluation protocol=Frozen feature probing, Params=170M, Modality=A+V, Pre-train data=AS2026.0693.6
SSLAMEvaluation protocol=Frozen feature probing, Params=88M, Modality=A, Pre-train data=AS2026.0693.2
EquiAVEvaluation protocol=Frozen feature probing, Params=170M, Modality=A+V, Pre-train data=AS2026.0693.2
Dasheng-1.2BEvaluation protocol=Frozen feature probing, Params=1.2B, Modality=A, Pre-train data=272k hrs mix2026.0692.2
MAViLEvaluation protocol=Frozen feature probing, Params=170M, Modality=A+V, Pre-train data=IN+AS2026.0690.8
SPEAREvaluation protocol=Frozen feature probing, Params=600M, Modality=A, Pre-train data=197k hrs mix2026.0689.4
CAV-MAE SyncEvaluation protocol=Frozen feature probing, Params=170M, Modality=A+V, Pre-train data=AS2026.0689.2
CAV-MAEEvaluation protocol=Frozen feature probing, Params=170M, Modality=A+V, Pre-train data=IN+AS2026.0677.5
AJEPAEvaluation protocol=Frozen feature probing, Params=85M, Modality=A, Pre-train data=AS2026.0674.4