Image Classification on MNIST (test) (Macro F1-score)
96.3Macro F1Deep Arguing
Evaluation Results
| Method | Links | |
|---|---|---|
| Deep ArguingBackbone=CNN2026.05 | 96.3 | |
| CATr1=0, r2=1:12026.04 | 94.9 | |
| MAMr1=0, r2=1:12026.04 | 94.5 | |
| MLPr1=0, r2=1:12026.04 | 94.2 | |
| XGBoostr1=0, r2=1:12026.04 | 94.1 | |
| Var-T-JEPABackbone=DCNv2, Evaluation Coverage=50%2026.03 | 93.6 | |
| Var-T-JEPABackbone=ResNet, Evaluation Coverage=50%2026.03 | 93.6 | |
| DNNBackbone=CNN2026.05 | 93.52 | |
| GIWr1=0, r2=1:12026.04 | 93.3 | |
| CSAMr1=0, r2=1:12026.04 | 92.1 | |
| Var-T-JEPABackbone=FT-Trans, Evaluation Coverage=50%2026.03 | 91.8 | |
| RSAMr1=0, r2=1:12026.04 | 91.7 | |
| MAMr1=0, r2=1:102026.04 | 91.4 | |
| Var-T-JEPABackbone=XGBoost, Evaluation Coverage=50%2026.03 | 91.3 | |
| SpAMr1=0, r2=1:12026.04 | 91.3 | |
| GIWr1=0, r2=1:102026.04 | 91.2 | |
| Var-T-JEPABackbone=DCNv2, Evaluation Coverage=20%2026.03 | 90.8 | |
| MAMr1=20%, r2=1:102026.04 | 90.5 | |
| GIWr1=20%, r2=1:102026.04 | 90.3 | |
| Var-T-JEPABackbone=MLP, Evaluation Coverage=50%2026.03 | 90.1 | |
| KANr1=0, r2=1:12026.04 | 90.1 | |
| Var-T-JEPABackbone=ResNet, Evaluation Coverage=20%2026.03 | 90 | |
| CATr1=0, r2=1:102026.04 | 89.8 | |
| Var-T-JEPABackbone=DCNv2, Evaluation Coverage=10%2026.03 | 89.7 | |
| XGBoostr1=0, r2=1:102026.04 | 89.4 | |
| Var-T-JEPABackbone=FT-Trans, Evaluation Coverage=20%2026.03 | 89.1 | |
| MLPr1=0, r2=1:102026.04 | 89.1 | |
| Var-T-JEPABackbone=XGBoost, Evaluation Coverage=20%2026.03 | 88.9 | |
| Var-T-JEPABackbone=ResNet, Evaluation Coverage=10%2026.03 | 88.8 | |
| Var-T-JEPABackbone=DCNv2, Evaluation Coverage=100%2026.03 | 88.4 | |
| Var-T-JEPABackbone=XGBoost, Evaluation Coverage=10%2026.03 | 88.3 | |
| XGBoostBackbone=XGBoost, Evaluation Coverage=100%2026.03 | 88.1 | |
| Var-T-JEPABackbone=AutoInt, Evaluation Coverage=50%2026.03 | 87.9 | |
| Var-T-JEPABackbone=FT-Trans, Evaluation Coverage=10%2026.03 | 87.9 | |
| FT-TransBackbone=FT-Trans, Evaluation Coverage=100%2026.03 | 87.7 | |
| DCNv2Backbone=DCNv2, Evaluation Coverage=100%2026.03 | 87.5 | |
| Var-T-JEPABackbone=ResNet, Evaluation Coverage=100%2026.03 | 87.2 | |
| Var-T-JEPABackbone=XGBoost, Evaluation Coverage=100%2026.03 | 87.1 | |
| T-JEPABackbone=XGBoost, Evaluation Coverage=100%2026.03 | 87 | |
| Var-T-JEPABackbone=FT-Trans, Evaluation Coverage=100%2026.03 | 86.4 | |
| NAMr1=0, r2=1:12026.04 | 86.4 | |
| CSAMr1=0, r2=1:102026.04 | 86.4 | |
| ResNetBackbone=ResNet, Evaluation Coverage=100%2026.03 | 86 | |
| RSAMr1=0, r2=1:102026.04 | 86 | |
| Var-T-JEPABackbone=MLP, Evaluation Coverage=20%2026.03 | 85.7 | |
| T-JEPABackbone=ResNet, Evaluation Coverage=100%2026.03 | 85.6 | |
| SpAMr1=0, r2=1:102026.04 | 85.6 | |
| KANr1=0, r2=1:102026.04 | 85.3 | |
| RSAMr1=20%, r2=1:102026.04 | 85.1 | |
| CSAMr1=20%, r2=1:102026.04 | 84.9 | |
| Var-T-JEPABackbone=MLP, Evaluation Coverage=10%2026.03 | 84 | |
| T-JEPABackbone=DCNv2, Evaluation Coverage=100%2026.03 | 84 | |
| Var-T-JEPABackbone=AutoInt, Evaluation Coverage=20%2026.03 | 84 | |
| CATr1=20%, r2=1:102026.04 | 83.9 | |
| XGBoostr1=20%, r2=1:102026.04 | 83.4 | |
| NAMr1=0, r2=1:102026.04 | 83.1 | |
| MLPr1=20%, r2=1:102026.04 | 83 | |
| Var-T-JEPABackbone=AutoInt, Evaluation Coverage=10%2026.03 | 82.4 | |
| Var-T-JEPABackbone=MLP, Evaluation Coverage=100%2026.03 | 82.3 | |
| MLPBackbone=MLP, Evaluation Coverage=100%2026.03 | 82.2 | |
| KANr1=20%, r2=1:102026.04 | 82 | |
| T-JEPABackbone=AutoInt, Evaluation Coverage=100%2026.03 | 81.6 | |
| SpAMr1=20%, r2=1:102026.04 | 81.1 | |
| Var-T-JEPABackbone=AutoInt, Evaluation Coverage=100%2026.03 | 81 | |
| AutoIntBackbone=AutoInt, Evaluation Coverage=100%2026.03 | 80.9 | |
| NAMr1=20%, r2=1:102026.04 | 80.4 | |
| T-JEPABackbone=FT-Trans, Evaluation Coverage=100%2026.03 | 26.9 | |
| T-JEPABackbone=MLP, Evaluation Coverage=100%2026.03 | 2.3 |