Salient Object Detection On Ecssd 1
평가 지표
E-measure
MAE
S-measure
max_F1
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | E-measure | MAE | S-measure | max_F1 | Paper Title | Repository |
|---|---|---|---|---|---|---|
| EVPv1 | 0.957 | 0.027 | 0.935 | 0.960 | Explicit Visual Prompting for Low-Level Structure Segmentations | |
| LDF(ours) | 0.924 | 0.033 | 0.924 | 0.950 | Label Decoupling Framework for Salient Object Detection | |
| EVPv2 | 0.957 | 0.028 | 0.935 | 0.958 | Explicit Visual Prompting for Universal Foreground Segmentations | |
| SelfReformer-Swin | 0.935 | 0.025 | 0.941 | 0.963 | SelfReformer: Self-Refined Network with Transformer for Salient Object Detection | |
| RCSB | 0.923 | 0.033 | 0.921 | 0.945 | Recursive Contour Saliency Blending Network for Accurate Salient Object Detection | |
| SelfReformer | 0.928 | 0.027 | 0.935 | 0.957 | SelfReformer: Self-Refined Network with Transformer for Salient Object Detection | |
| SAM2-UNet | 0.970 | 0.020 | 0.950 | - | SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation | |
| F3Net | - | 0.041 | 0.918 | 0.885 | U$^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection | |
| F3Net | 0.927 | 0.033 | 0.924 | 0.945 | F3Net: Fusion, Feedback and Focus for Salient Object Detection |
0 of 9 row(s) selected.