cs.CVNov 3, 2026

Learning to Falsify: Hierarchical Multiple Instance Learning for High Resolution AI-Generated Image Detection

Authors: Haoran Chen, Daiqi Gao, Xinyuan Li, Yongwei Wang, Lei Zhu, Rui Cai, Jianfeng Dong

Organizations: Zhejiang Gongshang University, Hangzhou, Zhejiang, China · Zhejiang University, Hangzhou, Zhejiang, China · The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, China · Zhejiang Key Laboratory of Big Data and Future E-Commerce Technology, Hangzhou, Zhejiang, China

Abstract

Recent advances in generative models have made synthetic images increasingly photorealistic, posing growing challenges to reliable and generalizable detection of AI-generated images. Existing methods typically rely on holistic image-level classification, which may overlook local artifacts, especially in high-resolution images. To address this limitation, we formulate this task as a falsification-driven multiple instance learning problem, where a single fake patch can falsify the whole image, while a real image requires all patches to be authentic. Based on this formulation, we propose Learning to Falsify (LTF), a hierarchical multiple instance learning framework that models an image as multiple bags of instances across different spatial levels and aggregates their predictions under the falsification-inspired principle. We further introduce Cross-Shuffle during training to encourage the model to learn local artifact evidence rather than image-level shortcuts. Furthermore, we propose the Falsification-driven Test-time Aggregation Strategy (FATAS), a plug-and-play module that extends the same falsification-inspired principle to existing detectors by aggregating patch-level predictions. Extensive experiments demonstrate that LTF achieves strong generalization and robustness across multiple benchmarks, while FATAS substantially improves representative detectors in high-resolution scenarios without retraining. Code is available at https://github.com/HuiGuanLab/LTF.git

Figures & tables

Explore similar work

CardsList
  1. SimLBR: Learning to Detect Fake Images by Learning to Detect Real Images

    Feb 23, 2026Aayush Dhakal, Subash Khanal, Srikumar Sastry +4AI-Generated Image DetectionOOD Generalization

  2. FAIR: Feature-Augmented Implicit Regularization for AI-generated Fake Image Detection

    Jul 24, 2026Md Redwanul Haque, Manzur Murshed, Manoranjan Paul +1Domain GeneralizationAI-Generated Image Detection

  3. Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detection

    May 14, 2026Yiheng Li, Yang Yang, Zichang Tan +3Synthetic Data AugmentationMixture of Experts