Image Classification on Mini-ImageNet (val)
87.08Peak AccuracySwin-T-EQ-R
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Swin-T-EQ-RImage Size=224^2, Param.=14M, Equivariance=mirror reflection2026.02 | 87.08 | 97.52 | |
| Swin-TImage Size=224^2, Param.=28M2026.02 | 87.06 | 97.46 | |
| XCiT-M24Image Size=224^2, Param.=84M2026.02 | 86.8 | 96.38 | |
| XCiT-S24Image Size=224^2, Param.=26M2026.02 | 85.79 | 96.31 | |
| MentorMixtraining_setting=Fine-tuned, noise_type=Blue, backbone=Inception-ResNet-v22019.11 | 84.2 | — | |
| MentorMixtraining_setting=Fine-tuned, noise_type=Red, backbone=Inception-ResNet-v22019.11 | 83.3 | — | |
| Bootstraptraining_setting=Fine-tuned, noise_type=Blue, backbone=Inception-ResNet-v22019.11 | 83.1 | — | |
| MentorNettraining_setting=Fine-tuned, noise_type=Blue, backbone=Inception-ResNet-v22019.11 | 82.9 | — | |
| Dropouttraining_setting=Fine-tuned, noise_type=Blue, backbone=Inception-ResNet-v22019.11 | 82.8 | — | |
| Bootstraptraining_setting=Fine-tuned, noise_type=Red, backbone=Inception-ResNet-v22019.11 | 82.7 | — | |
| Mixuptraining_setting=Fine-tuned, noise_type=Red, backbone=Inception-ResNet-v22019.11 | 82.4 | — | |
| MentorNettraining_setting=Fine-tuned, noise_type=Red, backbone=Inception-ResNet-v22019.11 | 82.4 | — | |
| Vanillatraining_setting=Fine-tuned, noise_type=Blue, backbone=Inception-ResNet-v22019.11 | 82.3 | — | |
| S-Modeltraining_setting=Fine-tuned, noise_type=Blue, backbone=Inception-ResNet-v22019.11 | 82.3 | — | |
| S-Modeltraining_setting=Fine-tuned, noise_type=Red, backbone=Inception-ResNet-v22019.11 | 82 | — | |
| WeightDecaytraining_setting=Fine-tuned, noise_type=Blue, backbone=Inception-ResNet-v22019.11 | 81.9 | — | |
| Dropouttraining_setting=Fine-tuned, noise_type=Red, backbone=Inception-ResNet-v22019.11 | 81.8 | — | |
| Mixuptraining_setting=Fine-tuned, noise_type=Blue, backbone=Inception-ResNet-v22019.11 | 81.7 | — | |
| Vanillatraining_setting=Fine-tuned, noise_type=Red, backbone=Inception-ResNet-v22019.11 | 81.6 | — | |
| WeightDecaytraining_setting=Fine-tuned, noise_type=Red, backbone=Inception-ResNet-v22019.11 | 81.5 | — | |
| DeiT-BImage Size=224^2, Param.=86M2026.02 | 72.43 | 90.14 | |
| MentorMixtraining_setting=Trained from scratch, noise_type=Blue, backbone=Inception-ResNet-v22019.11 | 70.9 | — | |
| DeiT-SImage Size=224^2, Param.=22M2026.02 | 70.83 | 89.74 | |
| MentorMixtraining_setting=Trained from scratch, noise_type=Red, backbone=Inception-ResNet-v22019.11 | 67 | — | |
| Mixuptraining_setting=Trained from scratch, noise_type=Red, backbone=Inception-ResNet-v22019.11 | 66 | — | |
| Dropouttraining_setting=Trained from scratch, noise_type=Red, backbone=Inception-ResNet-v22019.11 | 65.7 | — | |
| Bootstraptraining_setting=Trained from scratch, noise_type=Red, backbone=Inception-ResNet-v22019.11 | 65.5 | — | |
| MentorNettraining_setting=Trained from scratch, noise_type=Red, backbone=Inception-ResNet-v22019.11 | 65.1 | — | |
| Vanillatraining_setting=Trained from scratch, noise_type=Red, backbone=Inception-ResNet-v22019.11 | 64.9 | — | |
| S-Modeltraining_setting=Trained from scratch, noise_type=Red, backbone=Inception-ResNet-v22019.11 | 64.6 | — | |
| MentorNettraining_setting=Trained from scratch, noise_type=Blue, backbone=Inception-ResNet-v22019.11 | 61.8 | — | |
| Mixuptraining_setting=Trained from scratch, noise_type=Blue, backbone=Inception-ResNet-v22019.11 | 60.7 | — | |
| Bootstraptraining_setting=Trained from scratch, noise_type=Blue, backbone=Inception-ResNet-v22019.11 | 60.1 | — | |
| Dropouttraining_setting=Trained from scratch, noise_type=Blue, backbone=Inception-ResNet-v22019.11 | 59.3 | — | |
| S-Modeltraining_setting=Trained from scratch, noise_type=Blue, backbone=Inception-ResNet-v22019.11 | 58.7 | — | |
| Vanillatraining_setting=Trained from scratch, noise_type=Blue, backbone=Inception-ResNet-v22019.11 | 58.3 | — |