研究如何让合成图像检测器在真实场景中更可靠，提出实用训练指南。
Present and Future Generalization of Synthetic Image Detectors
- 系统分析数据源、训练方法和图像变换对检测器泛化能力的影响。
- 发现现有检测器在跨场景测试中表现不一，无通用有效方案。
- 提出改进策略，提升检测器在真实应用中的准确性和鲁棒性。
日益逼真的图像生成模型不断涌现，推动了对合成图像检测器的需求。为构建高效检测器，必须理解数据源多样性、训练方法和图像变换等因素对其泛化能力的影响。本文通过系统性分析，提出实用训练指南。在不同设置（如规模、数据来源、图像变换）下评估模型泛化性能，涵盖真实部署条件。通过对多种前沿检测器在多样且近期数据集上的广泛基准测试，发现尽管当前方法在特定场景表现优异，但无一能实现普适有效。识别出检测器的关键缺陷，并提出应对方案，支持真实场景检测应用的部署，显著提升准确性、可靠性与鲁棒性，突破现有系统局限。
原文摘要 · Abstract (English)
The continued release of increasingly realistic image generation models creates a demand for synthetic image detectors. To build effective detectors we must first understand how factors like data source diversity, training methodologies and image alterations affect their generalization capabilities. This work conducts a systematic analysis and uses its insights to develop practical guidelines for training robust synthetic image detectors. Model generalization capabilities are evaluated across different setups (e.g. scale, sources, transformations) including real-world deployment conditions. Through an extensive benchmarking of state-of-the-art detectors across diverse and recent datasets, we show that while current approaches excel in specific scenarios, no single detector achieves universal effectiveness. Critical flaws are identified in detectors, and workarounds are proposed to enable the deployment of real-world detector applications enhancing accuracy, reliability and robustness beyond the limitations of current systems.
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。