HyperAI초신경

Image Manipulation Detection On Dso 1

평가 지표

AUC

Balanced Accuracy

평가 결과

이 벤치마크에서 각 모델의 성능 결과

			Paper Title
TruFor	.984	.930	TruFor: Leveraging all-round clues for trustworthy image forgery detection and localization
Early Fusion	.966	.935	MMFusion: Combining Image Forensic Filters for Visual Manipulation Detection and Localization
Late Fusion	.958	.830	MMFusion: Combining Image Forensic Filters for Visual Manipulation Detection and Localization
ManTraNet	.874	.500	ManTra-Net: Manipulation Tracing Network for Detection and Localization of Image Forgeries With Anomalous Features
DF-Net	0.769	-	DF-Net: The Digital Forensics Network for Image Forgery Detection
CAT-Net v2	.747	.525	Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization
SPAN	.669	.233	SPAN: Spatial Pyramid Attention Network for Image Manipulation Localization
CR-CNN	.576	.289	Constrained R-CNN: A general image manipulation detection model
MVSS-Net	.552	.358	Image Manipulation Detection by Multi-View Multi-Scale Supervision

0 of 9 row(s) selected.

Image Manipulation Detection On Dso 1 | SOTA | HyperAI초신경