Semantic Segmentation on Oxford Pet small mask version - PET_S
0.179CE LossResNet34
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| ResNet34Pre-training=ImageNet-1K2024.11 | 0.179 | 90.98 | 80.1 | |
| ResNet50Pre-training=ImageNet-1K2024.11 | 0.189 | 93.03 | 81.5 | |
| U-Net4Pre-training=None, Downsampling layers=42024.11 | 0.243 | 77.17 | 71.3 | |
| MobileNetPre-training=ImageNet-1K2024.11 | 0.262 | 60.91 | 66.4 | |
| OneNete, 4Pre-training=None, Downsampling layers=4, Architecture configuration=encoder swap2024.11 | 0.309 | 51.76 | 63.6 | |
| OneNeted, 4Pre-training=None, Downsampling layers=4, Architecture configuration=encoder-decoder swap2024.11 | 0.437 | 21.79 | 53.5 |