Haoyi Deng — accepted AI-conference papers

2025

Reinforced Multi-teacher Knowledge Distillation for Efficient General Image Forgery Detection and Localization

Zeqin Yu, Jiangqun Ni, Jian Zhang, Haoyi Deng, Yuzhen Lin

AAAI 2025technical

Image forgery detection and localization (IFDL) is of vital importance as forged images can spread misinformation that poses potential threats to our daily life. However, previous methods still struggled to effectively handle forged images processed with diverse forgery operations in real-world scen…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

DiffForensics: Leveraging Diffusion Prior to Image Forgery Detection and Localization

Zeqin Yu, Jiangqun Ni, Yuzhen Lin, Haoyi Deng, Bin Li

CVPR 2024poster

As manipulating images may lead to misinterpretation of the visual content addressing the image forgery detection and localization (IFDL) problem has drawn serious public concerns. In this work we propose a simple assumption that the effective forensic method should focus on the mesoscopic propertie…

Cited by 20 Source ↗PDF ↗Scholar ↗