Image Classification on Weather
98.22AccuracyIndividual
Evaluation results
| Method | Links | |
|---|---|---|
| IndividualBackbone=ViT-B/16, Pre-trained=ImageNet-21k, Number of Merged Models=12024.05 | 98.22 | |
| EMR-MERGINGBackbone=ViT-B/16, Pre-trained=ImageNet-21k, Number of Merged Models=302024.05 | 97.76 | |
| AdaMergingBackbone=ViT-B/16, Pre-trained=ImageNet-21k, Number of Merged Models=302024.05 | 89.13 | |
| RegMeanBackbone=ViT-B/16, Pre-trained=ImageNet-21k, Number of Merged Models=302024.05 | 86.62 | |
| MARICbackbone=LLaVA 1.5-13B, zero-shot=true, parameter-update=none, temperature=02025.09 | 85.2 | |
| Chain-of-Thought (CoT)backbone=LLaVA 1.5-13B, zero-shot=true, parameter-update=none, temperature=02025.09 | 81.1 | |
| Task ArithmeticBackbone=ViT-B/16, Pre-trained=ImageNet-21k, Number of Merged Models=302024.05 | 74.56 | |
| Ties-MergingBackbone=ViT-B/16, Pre-trained=ImageNet-21k, Number of Merged Models=302024.05 | 72.86 | |
| Chain-of-Thought (CoT)backbone=LLaVA 1.5-7B, zero-shot=true, parameter-update=none, temperature=02025.09 | 70.1 | |
| MARICbackbone=LLaVA 1.5-7B, zero-shot=true, parameter-update=none, temperature=02025.09 | 65.6 | |
| SAVRbackbone=LLaVA 1.5-13B, zero-shot=true, parameter-update=none, temperature=02025.09 | 63 | |
| Weight AveragingBackbone=ViT-B/16, Pre-trained=ImageNet-21k, Number of Merged Models=302024.05 | 61.06 | |
| Direct Generationbackbone=LLaVA 1.5-7B, zero-shot=true, parameter-update=none, temperature=02025.09 | 50.2 | |
| SAVRbackbone=LLaVA 1.5-7B, zero-shot=true, parameter-update=none, temperature=02025.09 | 48 | |
| Direct Generationbackbone=LLaVA 1.5-13B, zero-shot=true, parameter-update=none, temperature=02025.09 | 21.7 |