Salient Object Detection On Pascal S 1
評価指標
E-measure
MAE
S-measure
max_F1
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | E-measure | MAE | S-measure | max_F1 | Paper Title | Repository |
|---|---|---|---|---|---|---|
| EVPv2 | 0.917 | 0.053 | 0.879 | 0.869 | Explicit Visual Prompting for Universal Foreground Segmentations | |
| SelfReformer-Swin | 0.874 | 0.049 | 0.877 | 0.896 | SelfReformer: Self-Refined Network with Transformer for Salient Object Detection | |
| SelfReformer | 0.872 | 0.050 | 0.874 | 0.894 | SelfReformer: Self-Refined Network with Transformer for Salient Object Detection | |
| SAM2-UNet | 0.931 | 0.043 | 0.894 | - | SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation | |
| EVPv1 | 0.917 | 0.054 | 0.878 | 0.872 | Explicit Visual Prompting for Low-Level Structure Segmentations | |
| F3Net | 0.858 | 0.061 | 0.854 | 0.871 | F3Net: Fusion, Feedback and Focus for Salient Object Detection | |
| RCSB | 0.853 | 0.059 | 0.854 | 0.875 | Recursive Contour Saliency Blending Network for Accurate Salient Object Detection | |
| F3Net | - | 0.086 | 0.831 | 0.768 | U$^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection | |
| LDF(ours) | 0.865 | 0.059 | 0.856 | 0.874 | Label Decoupling Framework for Salient Object Detection |
0 of 9 row(s) selected.