Image Classification on EuroSAT (Accuracy, NLL, ECE, Brier)
98.98AccuracySOAP
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| 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 | 98.98 | 0.042 | 71 | 0.017 | |
| 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 | 98.87 | 0.035 | 67 | 0.018 | |
| 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 | 98.78 | 0.034 | 43 | 0.018 | |
| 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 | 98.72 | 0.044 | 57 | 0.02 | |
| 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 | 98.71 | 0.042 | 61 | 0.02 | |
| 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 | 98.32 | 0.055 | 89 | 0.026 |