AI RESEARCH
Can We Build a Monolithic Model for Fake Image Detection? SICA: Semantic-Induced Constrained Adaptation for Unified-Yet-Discriminative Artifact Feature Space Reconstruction
arXiv CS.CV
•
ArXi:2602.06676v2 Announce Type: replace Fake Image Detection (FID), aiming at unified detection across four image forensic subdomains, is critical in real-world forensic scenarios. Compared with ensemble approaches, monolithic FID models are theoretically promising, but to date, consistently yield inferior performance in practice.