Image Manipulation Detection On Casia V1
평가 지표
AUC
Balanced Accuracy
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | AUC | Balanced Accuracy | Paper Title | Repository |
|---|---|---|---|---|
| Early Fusion | .929 | .845 | MMFusion: Combining Image Forensic Filters for Visual Manipulation Detection and Localization | - |
| TruFor | .916 | .813 | TruFor: Leveraging all-round clues for trustworthy image forgery detection and localization | - |
| DF-Net | .906 | - | DF-Net: The Digital Forensics Network for Image Forgery Detection | |
| MVSS-Net | .932 | .528 | Image Manipulation Detection by Multi-View Multi-Scale Supervision | - |
| Late Fusion | .930 | .860 | MMFusion: Combining Image Forensic Filters for Visual Manipulation Detection and Localization | - |
| CAT-Net v2 | .942 | .838 | Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization | - |
| ManTraNet | .644 | .500 | ManTra-Net: Manipulation Tracing Network for Detection and Localization of Image Forgeries With Anomalous Features | |
| CR-CNN | .670 | .481 | Constrained R-CNN: A general image manipulation detection model | - |
| SPAN | .480 | .112 | SPAN: Spatial Pyramid Attention Network for Image Manipulation Localization |
0 of 9 row(s) selected.