Image Classification on CIFAR-100 ST-100 step-imbalance (test)
60.17AccuracyGRAIN
Evaluation results
| Method | Links | ||
|---|---|---|---|
| GRAINBackbone=ViT-base, Fine-tuning strategy=FFT + GRAIN2026.06 | 60.17 | 0.43 | |
| SAMBackbone=ViT-base, Fine-tuning strategy=FFT + SAM2026.06 | 58.5 | 1.6 | |
| FocalLossBackbone=ViT-base, Fine-tuning strategy=FFT + FocalLoss2026.06 | 57.19 | 2.49 | |
| NoisyTuneBackbone=ViT-base, Fine-tuning strategy=FFT + NoisyTune2026.06 | 57.17 | 1.11 | |
| ViT (FFT)Backbone=ViT-base, Fine-tuning strategy=FFT2026.06 | 56.73 | 1.58 | |
| PCGradBackbone=ViT-base, Fine-tuning strategy=FFT + PCGrad2026.06 | 50.01 | 1.18 | |
| SWABackbone=ViT-base, Fine-tuning strategy=FFT + SWA2026.06 | 35.62 | 18.6 |