Image Classification on CIFAR-10 ST-100 step-imbalance (test)
85.17AccuracyGRAIN
Evaluation results
| Method | Links | ||
|---|---|---|---|
| GRAINBackbone=ViT-base, Fine-tuning strategy=FFT + GRAIN2026.06 | 85.17 | 0.9 | |
| ViT (FFT)Backbone=ViT-base, Fine-tuning strategy=FFT2026.06 | 83.27 | 2.13 | |
| SAMBackbone=ViT-base, Fine-tuning strategy=FFT + SAM2026.06 | 82.77 | 1.12 | |
| PCGradBackbone=ViT-base, Fine-tuning strategy=FFT + PCGrad2026.06 | 82.05 | 3.57 | |
| FocalLossBackbone=ViT-base, Fine-tuning strategy=FFT + FocalLoss2026.06 | 70.31 | 14.22 | |
| NoisyTuneBackbone=ViT-base, Fine-tuning strategy=FFT + NoisyTune2026.06 | 68.86 | 15.4 | |
| SWABackbone=ViT-base, Fine-tuning strategy=FFT + SWA2026.06 | 45.66 | 4.8 |