Image Manipulation Detection On Columbia
평가 지표
AUC
Balanced Accuracy
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | AUC | Balanced Accuracy | Paper Title | Repository |
|---|---|---|---|---|
| TruFor | .996 | .984 | TruFor: Leveraging all-round clues for trustworthy image forgery detection and localization | - |
| CR-CNN | .755 | .631 | Constrained R-CNN: A general image manipulation detection model | - |
| CAT-Net v2 | .977 | .803 | Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization | - |
| ManTraNet | .810 | .500 | ManTra-Net: Manipulation Tracing Network for Detection and Localization of Image Forgeries With Anomalous Features | |
| DF-Net | 0.880 | - | DF-Net: The Digital Forensics Network for Image Forgery Detection | |
| Late Fusion | .977 | .822 | MMFusion: Combining Image Forensic Filters for Visual Manipulation Detection and Localization | - |
| MVSS-Net | .984 | .729 | Image Manipulation Detection by Multi-View Multi-Scale Supervision | - |
| Early Fusion | .996 | .962 | MMFusion: Combining Image Forensic Filters for Visual Manipulation Detection and Localization | - |
0 of 8 row(s) selected.