Image Manipulation Detection On Casia V1

Metrics

AUC

Balanced Accuracy

Results

Performance results of various models on this benchmark

			Paper Title
CAT-Net v2	.942	.838	Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization
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
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
CR-CNN	.670	.481	Constrained R-CNN: A general image manipulation detection model
ManTraNet	.644	.500	ManTra-Net: Manipulation Tracing Network for Detection and Localization of Image Forgeries With Anomalous Features
SPAN	.480	.112	SPAN: Spatial Pyramid Attention Network for Image Manipulation Localization

0 of 9 row(s) selected.

Image Manipulation Detection On Casia V1 | SOTA | HyperAI