Image Classification on ImageNet-P (Corruption Robustness)
89.96Accuracy (Gaussian Noise)MoCo-v3 + SER
Evaluation results
| Method | Links | ||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| MoCo-v3 + SERBase Algorithm=MoCo-v3, variant=‡2026.03 | 89.96 | 87.41 | 89.93 | 90 | 82.5 | 90.1 | 90.08 | 83.23 | 89.15 | 87.3 | 89.93 | 87.8 | 89.68 | 75.8 | 88.29 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MoCo-v3 + E-SSLBase Algorithm=MoCo-v3, variant=‡2026.03 | 89.6 | 87.01 | 89.58 | 89.64 | 83.94 | 89.78 | 89.72 | 82.95 | 88.8 | 86.88 | 89.47 | 87.25 | 89.31 | 73.39 | 87.79 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MoCo-v3 + EquiModBase Algorithm=MoCo-v3, variant=†2026.03 | 88.78 | 85.66 | 88.79 | 88.75 | 80.86 | 88.93 | 88.98 | 80.16 | 87.95 | 83.41 | 88.68 | 86.38 | 88.51 | 71.89 | 87.13 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MoCo-v3 + SERBase Algorithm=MoCo-v32026.03 | 88.62 | 85.69 | 88.59 | 88.6 | 82.01 | 88.66 | 88.68 | 80.56 | 87.58 | 85.59 | 88.52 | 86.01 | 88.17 | 71.25 | 86.78 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MoCo-v3Base Algorithm=MoCo-v32026.03 | 87.75 | 84.67 | 87.81 | 87.82 | 80.34 | 87.91 | 87.94 | 79.22 | 86.75 | 84.54 | 87.72 | 85.16 | 87.48 | 69.08 | 85.84 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MoCo-v3 + AugSelfBase Algorithm=MoCo-v32026.03 | 87.58 | 84.69 | 87.5 | 87.59 | 80.81 | 87.73 | 87.67 | 79.7 | 86.5 | 83.07 | 87.66 | 85.25 | 87.31 | 71.44 | 85.83 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MoCo-v3 + STLBase Algorithm=MoCo-v32026.03 | 86.67 | 83.3 | 86.65 | 86.66 | 78.33 | 86.82 | 86.77 | 77.62 | 85.59 | 83.21 | 86.5 | 83.81 | 86.5 | 66.31 | 84.75 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MoCo-v3Base Model=MoCo-v32026.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 67.85 | 67.85 | 67.97 | 57.31 | 68.3 | 68.28 | 56.57 | 66.57 | 63.43 | 68.05 | 64.55 | 67.58 | 45.18 | 65.32 | 63.91 | |
| MoCo-v3 + AugSelfBase Model=MoCo-v3, Augmentation=AugSelf2026.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 67.44 | 67.47 | 67.47 | 57.51 | 67.76 | 67.81 | 56.77 | 66.15 | 60.77 | 67.39 | 64.41 | 67.1 | 47.15 | 64.96 | 63.58 | |
| MoCo-v3 + E-SSL‡Base Model=MoCo-v3, Technique=E-SSL, Variant=‡2026.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 70.26 | 70.19 | 70.22 | 61.49 | 70.65 | 70.54 | 60.6 | 68.87 | 65.82 | 70.27 | 66.92 | 69.82 | 48.86 | 67.59 | 66.58 | |
| MoCo-v3 + EquiMod†Base Model=MoCo-v3, Technique=EquiMod, Variant=†2026.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 68.6 | 68.7 | 68.78 | 57.08 | 69.17 | 69.13 | 56.97 | 67.51 | 60.88 | 68.75 | 65.18 | 68.27 | 47.04 | 66.17 | 64.44 | |
| MoCo-v3 + SERBase Model=MoCo-v3, Technique=SER2026.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 68.97 | 69.01 | 69 | 59.09 | 69.46 | 69.35 | 58.02 | 67.86 | 64.58 | 69.04 | 65.76 | 68.6 | 46.78 | 66.34 | 65.13 | |
| MoCo-v3 + SER‡Base Model=MoCo-v3, Technique=SER, Variant=‡2026.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 71.68 | 71.65 | 71.67 | 60.36 | 71.87 | 71.87 | 61.92 | 70.47 | 67.18 | 71.62 | 68.62 | 71.34 | 52.74 | 68.99 | 68 | |
| MoCo-v3 + STLBase Model=MoCo-v3, Technique=STL2026.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 66.19 | 66.14 | 66.15 | 54.97 | 66.29 | 66.32 | 54.38 | 64.71 | 61.16 | 66 | 62.07 | 65.86 | 42.53 | 63.17 | 61.85 |