Salient Object Detection on ECSSD 41 (test)
94.5MaxFPoolNet
Evaluation results
| Method | Links | ||
|---|---|---|---|
| PoolNetBackbone=ResNet-50, Training #Images=10,553, Training Dataset=DUTS-TR, joint training with edge detection=true2019.04 | 94.5 | 3.8 | |
| PoolNetBackbone=ResNet-50, Training #Images=10,553, Training Dataset=DUTS-TR, joint training with edge detection=false2019.04 | 94 | 4.2 | |
| PoolNetBackbone=VGG-16, Training #Images=10,553, Training Dataset=DUTS-TR, joint training with edge detection=true2019.04 | 93.7 | 4.4 | |
| PoolNetBackbone=VGG-16, Training #Images=10,553, Training Dataset=DUTS-TR, joint training with edge detection=false2019.04 | 93.6 | 4.7 | |
| PiCANetBackbone=ResNet-50, Training #Images=10,553, Training Dataset=DUTS-TR2019.04 | 93.2 | 4.8 | |
| PiCANetBackbone=VGG-16, Training #Images=10,553, Training Dataset=DUTS-TR2019.04 | 93 | 4.9 | |
| PoolNetBackbone=VGG-16, Training #Images=5,000, Training Dataset=MSRA-B + HKU-IS, joint training with edge detection=false2019.04 | 93 | 5.3 | |
| PAGRBackbone=VGG-16, Training #Images=10,553, Training Dataset=DUTS-TR2019.04 | 92.4 | 6.4 | |
| GearNetBackbone=VGG-16, Training #Images=5,000, Training Dataset=MSRA-B + HKU-IS2019.04 | 92.3 | 5.5 | |
| DGRLBackbone=ResNet-50, Training #Images=10,553, Training Dataset=DUTS-TR2019.04 | 92.1 | 4.3 | |
| PoolNetBackbone=VGG-16, Training #Images=2,500, Training Dataset=MSRA-B, joint training with edge detection=false2019.04 | 91.8 | 5.7 | |
| SRMBackbone=ResNet-50, Training #Images=10,553, Training Dataset=DUTS-TR2019.04 | 91.6 | 5.6 | |
| AmuletBackbone=VGG-16, Training #Images=10,000, Training Dataset=MSRA10K2019.04 | 91.1 | 6.2 | |
| UCFBackbone=VGG-16, Training #Images=10,000, Training Dataset=MSRA10K2019.04 | 90.8 | 8 | |
| DSSBackbone=VGG-16, Training #Images=2,500, Training Dataset=MSRA-B2019.04 | 90.6 | 6.4 | |
| DHSBackbone=VGG-16, Training #Images=9,500, Training Dataset=MSRA10K + DUT-OMRON2019.04 | 90.5 | 6.2 | |
| MSRBackbone=VGG-16, Training #Images=5,000, Training Dataset=MSRA-B + HKU-IS2019.04 | 90.3 | 5.9 | |
| NLDFBackbone=VGG-16, Training #Images=3,000, Training Dataset=MSRA-B2019.04 | 90.3 | 6.5 | |
| RFCNBackbone=VGG-16, Training #Images=10,000, Training Dataset=MSRA10K2019.04 | 89.8 | 9.7 | |
| DCLBackbone=VGG-16, Training #Images=2,500, Training Dataset=MSRA-B2019.04 | 89.6 | 8 |