Audio Classification on AudioSet 20k (train test)
31.67mAPprotobin
Evaluation Results
| Method | Links | |
|---|---|---|
| protobinBackbone=EAT, Input Category=Token Map (Prot), Pooling Method=protobin2025.09 | 31.67 | |
| protobinBackbone=BEATs, Input Category=Token Map (Prot), Pooling Method=protobin2025.09 | 31.54 | |
| protobinBackbone=SSLAM, Input Category=Token Map (Prot), Pooling Method=protobin2025.09 | 30.94 | |
| protobinBackbone=Dasheng, Input Category=Token Map (Prot), Pooling Method=protobin2025.09 | 29.94 | |
| protobinBackbone=A-MAE, Input Category=Token Map (Prot), Pooling Method=protobin2025.09 | 22.32 | |
| protoBackbone=ASiT, Input Category=Token Map (Prot), Pooling Method=proto2025.09 | 21.89 | |
| protoBackbone=A-MAE, Input Category=Token Map (Prot), Pooling Method=proto2025.09 | 21.61 | |
| protobinBackbone=ASiT, Input Category=Token Map (Prot), Pooling Method=protobin2025.09 | 20.96 | |
| mlpBackbone=ASiT, Input Category=[cls] Baseline, Pooling Method=mlp2025.09 | 19.16 | |
| linearBackbone=ASiT, Input Category=[cls] Baseline, Pooling Method=linear2025.09 | 18.35 | |
| mhcaBackbone=A-MAE, Input Category=Token Map (Att.), Pooling Method=mhca2025.09 | 17.09 | |
| epBackbone=A-MAE, Input Category=Token Map (Att.), Pooling Method=ep2025.09 | 17.03 | |
| linpreBackbone=A-MAE, Input Category=Token Map, Pooling Method=linpre2025.09 | 16.49 | |
| simpoolBackbone=A-MAE, Input Category=Token Map (Att.), Pooling Method=simpool2025.09 | 14.69 | |
| abmilpBackbone=A-MAE, Input Category=Token Map (Att.), Pooling Method=abmilp2025.09 | 14.24 | |
| convBackbone=A-MAE, Input Category=Token Map, Pooling Method=conv2025.09 | 11.87 | |
| linearcBackbone=A-MAE, Input Category=Token Map, Pooling Method=linearc2025.09 | 9.66 | |
| mlpBackbone=A-MAE, Input Category=[cls] Baseline, Pooling Method=mlp2025.09 | 8.77 | |
| linearBackbone=A-MAE, Input Category=[cls] Baseline, Pooling Method=linear2025.09 | 8.36 |