Audio Classification on AudioSet AS-2M
50.2mAP (%)CAT
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| CAT#Param=91M, Pre-training Data=AS2026.01 | 50.2 | — | — | — | |
| ASDA#Param=93M, Pre-training Data=AS2026.01 | 49 | — | — | — | |
| BEATs_iter3+#Param=90M, Pre-training Data=AS2026.01 | 48.6 | — | — | — | |
| A-JEPA#Param=86M, Pre-training Data=AS2026.01 | 48.6 | — | — | — | |
| EAT#Param=88M, Pre-training Data=AS2026.01 | 48.6 | — | — | — | |
| M2D-CLAP#Param=86M, Pre-training Data=TA+AS2026.01 | 48.5 | — | — | — | |
| BEATs_iter3#Param=90M, Pre-training Data=AS2026.01 | 48 | — | — | — | |
| ATST-Frame#Param=86M, Pre-training Data=AS2026.01 | 48 | — | — | — | |
| ASiT#Param=86M, Pre-training Data=AS2026.01 | 48 | — | — | — | |
| Audio-MAE#Param=86M, Pre-training Data=AS2026.01 | 47.3 | — | — | — | |
| PassT#Param=86M, Pre-training Data=IN2026.01 | 47.1 | — | — | — | |
| HTS-AT#Param=31M, Pre-training Data=IN2026.01 | 47.1 | — | — | — | |
| MaskSpec#Param=86M, Pre-training Data=AS2026.01 | 47.1 | — | — | — | |
| CLAP#Param=86M, Pre-training Data=TA2026.01 | 46.9 | — | — | — | |
| AST#Param=86M, Pre-training Data=IN2026.01 | 45.9 | — | — | — | |
| ATST-Clip#Param=86M, Pre-training Data=AS2026.01 | 45.2 | — | — | — | |
| PSLA#Param=14M, Pre-training Data=IN2026.01 | 44.4 | — | — | — | |
| MBT#Param=86M, Pre-training Data=IN-21K2026.01 | 44.3 | — | — | — | |
| PANN#Param=81M, Pre-training Data=-2026.01 | 43.1 | — | — | — | |
| Conformer#Param=88M, Pre-training Data=AS2026.01 | 41.1 | — | — | — | |
| AudioCLIP#Param=93M, Pre-training Data=TI+AS2026.01 | 25.9 | — | — | — | |
| ASTPT=IN-SL2022.12 | — | 45.9 | — | — | |
| Attn AVPT=IN-SL2022.12 | — | 38.4 | 25.7 | 44.2 | |
| Aud-MAEPT=AS-SSL2022.12 | — | 47.3 | — | — | |
| CAV-MAEPT=IN-SSL, AS-SSL2022.12 | — | 46.6 | 26.2 | 51.2 | |
| G-BlendPT=-2022.12 | — | 32.4 | 18.8 | 41.8 | |
| HTS-ATPT=IN-SL2022.12 | — | 47.1 | — | — | |
| MAViLPT=AS-SSL2022.12 | — | 48.7 | 28.3 | 51.9 | |
| MAViLPT=IN-SSL, AS-SSL2022.12 | — | 48.7 | 30.3 | 53.3 | |
| MBTPT=IN21K-SL2022.12 | — | 41.5 | 31.3 | 49.6 | |
| PANNSPT=-2022.12 | — | 43.9 | — | — | |
| PaSSTPT=IN-SL2022.12 | — | 47.1 | — | — | |
| PerceiverPT=-2022.12 | — | 38.4 | 25.8 | 44.2 |