Contamination Regression on Scrap Metal Dataset (test)
0.36MAE (railcar)Swin 2 B
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Swin 2 BPre-training=ImageNet-1K, Learning_Paradigm=Multi-task learning (MTL)2026.02 | 0.36 | 0.78 | |
| ViT B 16Pre-training=ImageNet-1K2026.02 | 0.48 | 0.66 | |
| ViT B 32Pre-training=ImageNet-1K2026.02 | 0.49 | 0.65 | |
| ResNeXt 101Pre-training=ImageNet-1K2026.02 | 0.55 | 0.58 | |
| ResNet 50Pre-training=ImageNet-1K2026.02 | 0.74 | 0.49 | |
| EfficientNet 7 BPre-training=ImageNet-1K2026.02 | 0.8 | 0.45 |