Image Manipulation Detection On Cocoglide
評価指標
AUC
Balanced Accuracy
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 | AUC | Balanced Accuracy | Paper Title | Repository |
|---|---|---|---|---|
| TruFor | .752 | .639 | TruFor: Leveraging all-round clues for trustworthy image forgery detection and localization | - |
| ManTraNet | .778 | .500 | ManTra-Net: Manipulation Tracing Network for Detection and Localization of Image Forgeries With Anomalous Features | - |
| SPAN | .475 | .298 | SPAN: Spatial Pyramid Attention Network for Image Manipulation Localization | - |
| CAT-Net v2 | .667 | .580 | Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization | |
| CR-CNN | .589 | .447 | Constrained R-CNN: A general image manipulation detection model | - |
| MVSS-Net | .654 | .117 | Image Manipulation Detection by Multi-View Multi-Scale Supervision | |
| Early Fusion | .755 | .660 | MMFusion: Combining Image Forensic Filters for Visual Manipulation Detection and Localization | |
| Late Fusion | .760 | .677 | MMFusion: Combining Image Forensic Filters for Visual Manipulation Detection and Localization |
0 of 8 row(s) selected.