Image Classification on GTSRB (Calibration Evaluation)
99.11AccuracyEVON
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 | 99.11 | 0.035 | 86 | 1.3 | |
| 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 | 99.02 | 0.059 | 58 | 1.7 | |
| 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 | 98.97 | 0.046 | 29 | 1.5 | |
| 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 | 98.74 | 0.051 | 60 | 1.8 | |
| 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 | 0.053 | 59 | 1.8 | |
| 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 | 98.4 | 0.07 | 75 | 2.4 |