通过多维度差异性设计，提升真实场景中AI生成图像的检测鲁棒性。
HEDGE: Heterogeneous Ensemble for Detection of AI-GEnerated Images in the Wild
- 构建三种互补检测路径：数据增强、多尺度特征与不同主干网络
- 在NTIRE 2026挑战赛中位列第4，多个基准上达领先水平
- 适合需要高鲁棒性检测能力的研究与应用开发者
真实世界中对AI生成图像的鲁棒检测仍具挑战，源于生成模型快速演进及多样现实失真。单一训练方式、分辨率或主干网络难以应对所有情况，需在多个维度引入结构化异质性。为此，提出HEDGE——一种针对真实场景中AI生成图像检测的异质集成方法，沿三个方向构建互补检测路径：多样化的强增广训练数据、多尺度特征提取、主干网络异质性。具体而言，路径A通过分阶段数据扩展与增广升级构建基于DINOv3的检测器；路径B引入更高分辨率分支以捕捉细粒度取证线索；路径C增加基于MetaCLIP2的分支以实现主干多样性。各路径输出通过逻辑空间加权平均融合，并由轻量级双门控机制优化，有效处理分支异常值与多数主导融合误差。HEDGE在NTIRE 2026‘真实场景中鲁棒AI生成图像检测’挑战赛中获第4名，在多个AIGC图像检测基准上达到当前最优性能，展现出强大鲁棒性。
原文摘要 · Abstract (English)
Robust detection of AI-generated images in the wild remains challenging due to the rapid evolution of generative models and varied real-world distortions. We argue that relying on a single training regime, resolution, or backbone is insufficient to handle all conditions, and that structured heterogeneity across these dimensions is essential for robust detection. To this end, we propose HEDGE, a Heterogeneous Ensemble for Detection of AI-GEnerated images, that introduces complementary detection routes along three axes: diverse training data with strong augmentation, multi-scale feature extraction, and backbone heterogeneity. Specifically, Route~A progressively constructs DINOv3-based detectors through staged data expansion and augmentation escalation, Route~B incorporates a higher-resolution branch for fine-grained forensic cues, and Route~C adds a MetaCLIP2-based branch for backbone diversity. All outputs are fused via logit-space weighted averaging, refined by a lightweight dual-gating mechanism that handles branch-level outliers and majority-dominated fusion errors. HEDGE achieves 4th place in the NTIRE 2026 Robust AI-Generated Image Detection in the Wild Challenge and attains state-of-the-art performance with strong robustness on multiple AIGC image detection benchmarks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。