Pixel-level Manipulation Detection on NIST
73.7F1 ScoreMVSS-Net
Evaluation Results
| Method | Links | |
|---|---|---|
| MVSS-NetThresholding strategy=Optimal threshold per model & testset, Training dataset=CASIAv22021.04 | 73.7 | |
| MVSS-NetThreshold Strategy=Optimal threshold per model & testset, Training Data=CASIAv22021.12 | 73.7 | |
| MVSS-Net++Threshold Strategy=Optimal threshold per model & testset, Training Data=CASIAv22021.12 | 71.5 | |
| SPANThreshold Strategy=Optimal threshold per model & testset, Training Data=Private2021.12 | 68.3 | |
| CAT-NetThreshold Strategy=Optimal threshold per model & testset, Training Data=Private2021.12 | 59.9 | |
| FCNThresholding strategy=Optimal threshold per model & testset, Training dataset=CASIAv22021.04 | 50.7 | |
| FCNThreshold Strategy=Optimal threshold per model & testset, Training Data=CASIAv22021.12 | 50.7 | |
| H-LSTMThreshold Strategy=Optimal threshold per model & testset, Training Data=Published but no longer publicly accessible data2021.12 | 46.6 | |
| GSR-NetThresholding strategy=Optimal threshold per model & testset, Training dataset=CASIAv22021.04 | 45.6 | |
| GSR-NetThreshold Strategy=Optimal threshold per model & testset, Training Data=CASIAv22021.12 | 45.6 | |
| ManTra-NetThresholding strategy=Optimal threshold per model & testset, Training dataset=Other (Not CASIAv2)2021.04 | 45.5 | |
| ManTra-NetThreshold Strategy=Optimal threshold per model & testset, Training Data=Private2021.12 | 45.5 | |
| CR-CNNThresholding strategy=Optimal threshold per model & testset, Training dataset=CASIAv22021.04 | 42.8 | |
| CR-CNNThreshold Strategy=Optimal threshold per model & testset, Training Data=CASIAv22021.12 | 42.8 | |
| MFCNThresholding strategy=Optimal threshold per model & testset, Training dataset=CASIAv22021.04 | 42.2 | |
| MFCNThreshold Strategy=Optimal threshold per model & testset, Training Data=CASIAv22021.12 | 42.2 | |
| HP-FCNThresholding strategy=Optimal threshold per model & testset, Training dataset=Other (Not CASIAv2)2021.04 | 36 | |
| HP-FCNThreshold Strategy=Optimal threshold per model & testset, Training Data=Private2021.12 | 36 | |
| H-LSTMThreshold Strategy=Fixed threshold (0.5), Training Data=Published but no longer publicly accessible data2021.12 | 35.4 | |
| MVSS-Net++Threshold Strategy=Fixed threshold (0.5), Training Data=CASIAv22021.12 | 30.4 | |
| MVSS-NetThresholding strategy=Fixed threshold (0.5), Training dataset=CASIAv22021.04 | 29.2 | |
| MVSS-NetThreshold Strategy=Fixed threshold (0.5), Training Data=CASIAv22021.12 | 29.2 | |
| GSR-NetThresholding strategy=Fixed threshold (0.5), Training dataset=CASIAv22021.04 | 28.3 | |
| GSR-NetThreshold Strategy=Fixed threshold (0.5), Training Data=CASIAv22021.12 | 28.3 | |
| CR-CNNThresholding strategy=Fixed threshold (0.5), Training dataset=CASIAv22021.04 | 23.8 | |
| CR-CNNThreshold Strategy=Fixed threshold (0.5), Training Data=CASIAv22021.12 | 23.8 | |
| SPANThreshold Strategy=Fixed threshold (0.5), Training Data=Private2021.12 | 22.1 | |
| CAT-NetThreshold Strategy=Fixed threshold (0.5), Training Data=Private2021.12 | 17.9 | |
| FCNThresholding strategy=Fixed threshold (0.5), Training dataset=CASIAv22021.04 | 16.7 | |
| FCNThreshold Strategy=Fixed threshold (0.5), Training Data=CASIAv22021.12 | 16.7 | |
| HP-FCNThresholding strategy=Fixed threshold (0.5), Training dataset=Other (Not CASIAv2)2021.04 | 12.1 | |
| HP-FCNThreshold Strategy=Fixed threshold (0.5), Training Data=Private2021.12 | 12.1 | |
| ManTra-NetThresholding strategy=Fixed threshold (0.5), Training dataset=Other (Not CASIAv2)2021.04 | 0 | |
| ManTra-NetThreshold Strategy=Fixed threshold (0.5), Training Data=Private2021.12 | 0 |