activity
20242026
collaborators

6 papers

cs.CV2026

Can We Build a Monolithic Model for Fake Image Detection? SICA: Semantic-Induced Constrained Adaptation for Unified-Yet-Discriminative Artifact Feature Space Reconstruction

Bo Du, Xiaochen Ma, Xuekang Zhu +8

Fake Image Detection (FID), aiming at unified detection across four image forensic subdomains, is critical in real-world forensic scenarios. Compared with ensemble approaches, mono…

cs.CV2026

DINOv3 Beats Specialized Detectors: A Simple Foundation Model Baseline for Image Forensics

Jieming Yu, Qiuxiao Feng, Zhuohan Wang +1

With the rapid advancement of deep generative models, realistic fake images have become increasingly accessible, yet existing localization methods rely on complex designs and still…

cs.CV2026

ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localization

Bo Du, Xuekang Zhu, Xiaochen Ma +6

The field of Fake Image Detection and Localization (FIDL) is highly fragmented, encompassing four domains: deepfake detection (Deepfake), image manipulation detection and localizat…

cs.CV2025

M^3:Manipulation Mask Manufacturer for Arbitrary-Scale Super-Resolution Mask

Xinyu Yang, Xiaochen Ma, Xuekang Zhu +5

In the field of image manipulation localization (IML), the small quantity and poor quality of existing datasets have always been major issues. A dataset containing various types of…

cs.CV2024

Can We Get Rid of Handcrafted Feature Extractors? SparseViT: Nonsemantics-Centered, Parameter-Efficient Image Manipulation Localization through Spare-Coding Transformer

Lei Su, Xiaochen Ma, Xuekang Zhu +3

Non-semantic features or semantic-agnostic features, which are irrelevant to image context but sensitive to image manipulations, are recognized as evidential to Image Manipulation…

cs.CV2024

Mesoscopic Insights: Orchestrating Multi-scale & Hybrid Architecture for Image Manipulation Localization

Xuekang Zhu, Xiaochen Ma, Lei Su +7

The mesoscopic level serves as a bridge between the macroscopic and microscopic worlds, addressing gaps overlooked by both. Image manipulation localization (IML), a crucial techniq…