Annotator Evaluation on CUB-200 2011 (test)
58.08Test AccuracyGBV
Evaluation results
| Method | Links | |
|---|---|---|
| GBVBackbone=ResNet-34, Pre-trained weights=ImageNet, tau parameter setting=best τ2026.04 | 58.08 | |
| GBVBackbone=ResNet-34, Pre-trained weights=ImageNet, tau parameter setting=quick τ2026.04 | 57.58 | |
| MMDBackbone=ResNet-34, Pre-trained weights=ImageNet2026.04 | 52.62 | |
| UniformBackbone=ResNet-34, Pre-trained weights=ImageNet2026.04 | 52.45 | |
| DAVINZBackbone=ResNet-34, Pre-trained weights=ImageNet2026.04 | 52.06 |