Image Classification on RESISC45 (Accuracy and Calibration)
95.79AccuracyEVON
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| EVONOptimizer=EVON, Monte Carlo samples (BMA)=32, Backbone=ViT-B/16, Pre-training=OpenAI CLIP, Fine-tuning protocol=linear layers (99% of parameters)2026.06 | 95.79 | 0.123 | 0.51 | 0.062 | |
| SOAPOptimizer=SOAP, Monte Carlo samples (BMA)=1, Backbone=ViT-B/16, Pre-training=OpenAI CLIP, Fine-tuning protocol=linear layers (99% of parameters)2026.06 | 95.74 | 0.161 | 2.48 | 0.067 | |
| AdamWOptimizer=AdamW, Monte Carlo samples (BMA)=1, Backbone=ViT-B/16, Pre-training=OpenAI CLIP, Fine-tuning protocol=linear layers (99% of parameters)2026.06 | 95.61 | 0.156 | 2.21 | 0.069 | |
| EVONOptimizer=EVON, Monte Carlo samples (BMA)=1, Backbone=ViT-B/16, Pre-training=OpenAI CLIP, Fine-tuning protocol=linear layers (99% of parameters)2026.06 | 95.31 | 0.18 | 2.7 | 0.071 | |
| IVONOptimizer=IVON, Monte Carlo samples (BMA)=32, Backbone=ViT-B/16, Pre-training=OpenAI CLIP, Fine-tuning protocol=linear layers (99% of parameters)2026.06 | 95.23 | 0.164 | 1.64 | 0.073 | |
| IVONOptimizer=IVON, Monte Carlo samples (BMA)=1, Backbone=ViT-B/16, Pre-training=OpenAI CLIP, Fine-tuning protocol=linear layers (99% of parameters)2026.06 | 95.17 | 0.183 | 2.5 | 0.077 |