Semantic Segmentation on REFUGE (test)
83.57mIoUDeCon-SL
Evaluation results
| Method | Links | |
|---|---|---|
| DeCon-SLPre-training Dataset=COCO, Label Percentage=100%, Transfer=enc, Loss=Lenc, Ldec2025.03 | 83.57 | |
| DeCon-SLPre-training Dataset=COCO, Label Percentage=100%, Transfer=enc + dec, Loss=Lenc, Ldec2025.03 | 83.25 | |
| SlotConPre-training Dataset=COCO, Label Percentage=100%, Transfer=enc, Loss=Lenc2025.03 | 82.83 | |
| DeCon-SLPre-training Dataset=Downstream (REFUGE), Label Percentage=100%, Transfer=enc + dec, Loss=Lenc, Ldec2025.03 | 81.01 | |
| DeCon-SLPre-training Dataset=Downstream (REFUGE), Label Percentage=100%, Transfer=enc, Loss=Lenc, Ldec2025.03 | 80.71 | |
| SlotConPre-training Dataset=Downstream (REFUGE), Label Percentage=100%, Transfer=enc, Loss=Lenc2025.03 | 79.86 | |
| DeCon-SLPre-training Dataset=COCO, Label Percentage=25%, Transfer=enc, Loss=Lenc, Ldec2025.03 | 78.92 | |
| SlotConPre-training Dataset=COCO, Label Percentage=25%, Transfer=enc, Loss=Lenc2025.03 | 77.8 | |
| DeCon-SLPre-training Dataset=COCO, Label Percentage=25%, Transfer=enc + dec, Loss=Lenc, Ldec2025.03 | 77.27 | |
| DeCon-SLPre-training Dataset=COCO, Label Percentage=5%, Transfer=enc + dec, Loss=Lenc, Ldec2025.03 | 72.09 | |
| DeCon-SLPre-training Dataset=COCO, Label Percentage=5%, Transfer=enc, Loss=Lenc, Ldec2025.03 | 71.75 | |
| SlotConPre-training Dataset=COCO, Label Percentage=5%, Transfer=enc, Loss=Lenc2025.03 | 69.6 | |
| Random init.Pre-training Dataset=None, Label Percentage=100%2025.03 | 62.82 | |
| Random init.Pre-training Dataset=None, Label Percentage=5%2025.03 | 49.53 | |
| Random init.Pre-training Dataset=None, Label Percentage=25%2025.03 | 41.41 |