Pixel-level Manipulation Detection on Columbia
77.6F1 ScoreCAT-Net
Evaluation Results
| Method | Links | |
|---|---|---|
| CAT-NetThreshold Strategy=Optimal threshold per model & testset, Training Data=Private2021.12 | 77.6 | |
| SPANThreshold Strategy=Optimal threshold per model & testset, Training Data=Private2021.12 | 77.4 | |
| MVSS-Net++Threshold Strategy=Optimal threshold per model & testset, Training Data=CASIAv22021.12 | 73.1 | |
| ManTra-NetThresholding strategy=Optimal threshold per model & testset, Training dataset=Other (Not CASIAv2)2021.04 | 70.9 | |
| ManTra-NetThreshold Strategy=Optimal threshold per model & testset, Training Data=Private2021.12 | 70.9 | |
| CR-CNNThresholding strategy=Optimal threshold per model & testset, Training dataset=CASIAv22021.04 | 70.4 | |
| CR-CNNThreshold Strategy=Optimal threshold per model & testset, Training Data=CASIAv22021.12 | 70.4 | |
| MVSS-NetThresholding strategy=Optimal threshold per model & testset, Training dataset=CASIAv22021.04 | 70.3 | |
| MVSS-NetThreshold Strategy=Optimal threshold per model & testset, Training Data=CASIAv22021.12 | 70.3 | |
| MVSS-Net++Threshold Strategy=Fixed threshold (0.5), Training Data=CASIAv22021.12 | 66 | |
| MVSS-NetThresholding strategy=Fixed threshold (0.5), Training dataset=CASIAv22021.04 | 63.8 | |
| MVSS-NetThreshold Strategy=Fixed threshold (0.5), Training Data=CASIAv22021.12 | 63.8 | |
| GSR-NetThresholding strategy=Optimal threshold per model & testset, Training dataset=CASIAv22021.04 | 62.2 | |
| GSR-NetThreshold Strategy=Optimal threshold per model & testset, Training Data=CASIAv22021.12 | 62.2 | |
| GSR-NetThresholding strategy=Fixed threshold (0.5), Training dataset=CASIAv22021.04 | 61.3 | |
| GSR-NetThreshold Strategy=Fixed threshold (0.5), Training Data=CASIAv22021.12 | 61.3 | |
| MFCNThresholding strategy=Optimal threshold per model & testset, Training dataset=CASIAv22021.04 | 61.2 | |
| MFCNThreshold Strategy=Optimal threshold per model & testset, Training Data=CASIAv22021.12 | 61.2 | |
| FCNThresholding strategy=Optimal threshold per model & testset, Training dataset=CASIAv22021.04 | 58.6 | |
| FCNThreshold Strategy=Optimal threshold per model & testset, Training Data=CASIAv22021.12 | 58.6 | |
| CAT-NetThreshold Strategy=Fixed threshold (0.5), Training Data=Private2021.12 | 55.5 | |
| SPANThreshold Strategy=Fixed threshold (0.5), Training Data=Private2021.12 | 48.7 | |
| HP-FCNThresholding strategy=Optimal threshold per model & testset, Training dataset=Other (Not CASIAv2)2021.04 | 47.1 | |
| HP-FCNThreshold Strategy=Optimal threshold per model & testset, Training Data=Private2021.12 | 47.1 | |
| CR-CNNThresholding strategy=Fixed threshold (0.5), Training dataset=CASIAv22021.04 | 43.6 | |
| CR-CNNThreshold Strategy=Fixed threshold (0.5), Training Data=CASIAv22021.12 | 43.6 | |
| ManTra-NetThresholding strategy=Fixed threshold (0.5), Training dataset=Other (Not CASIAv2)2021.04 | 36.4 | |
| ManTra-NetThreshold Strategy=Fixed threshold (0.5), Training Data=Private2021.12 | 36.4 | |
| FCNThresholding strategy=Fixed threshold (0.5), Training dataset=CASIAv22021.04 | 22.3 | |
| FCNThreshold Strategy=Fixed threshold (0.5), Training Data=CASIAv22021.12 | 22.3 | |
| H-LSTMThreshold Strategy=Optimal threshold per model & testset, Training Data=Published but no longer publicly accessible data2021.12 | 14.2 | |
| H-LSTMThreshold Strategy=Fixed threshold (0.5), Training Data=Published but no longer publicly accessible data2021.12 | 13 | |
| HP-FCNThresholding strategy=Fixed threshold (0.5), Training dataset=Other (Not CASIAv2)2021.04 | 8.7 | |
| HP-FCNThreshold Strategy=Fixed threshold (0.5), Training Data=Private2021.12 | 6.7 |