COMPASS：用于通用AIGI检测的上下文矩先验对齐
COMPASS: Contextual Moment Prior Alignment for Generalizable AIGI Detection
AI总结：
本研究针对通用AIGI与深度伪造检测的语义错位问题，提出数据感知子空间适配框架COMPASS，通过语义代理集实现矩先验对齐，在多类跨场景检测任务中达到最优性能。
摘要：
通用人工智能生成图像（AIGI）与深度伪造检测仍面临挑战，原因在于不对称现象——对有限训练分布的适配会降低视觉基础模型（VFM）的可迁移表示。近期的子空间适配方法通过冻结高幅值主成分、适配残差子空间缓解该问题，但这类基于幅值的分解与数据无关，未明确考虑目标相关语义，可能导致语义错位。我们提出COMPASS（用于子空间分离的上下文矩先验对齐），这是一种数据感知的子空间适配框架，利用小型未标注语义代理集估计目标激活统计量。COMPASS将激活协方差纳入预训练权重的分解，保留目标相关表示作为稳定语义参考，同时残差适配器学习伪造相关变化；代理校准无需基于梯度的优化。大量实验表明，其在跨数据集、跨方法、联合跨数据集-方法及开放世界跨生成器评估中均表现出强泛化性，在深度伪造与AIGI检测基准上均达到了最优性能。
英文摘要：
Generalizable AI-generated image (AIGI) and deepfake detection remain challenging due to the asymmetry phenomenon, where adaptation to limited training distributions can degrade the transferable representations of Vision Foundation Models (VFMs). Recent subspace adaptation methods mitigate this issue by freezing high-magnitude principal components while adapting the residual subspace. However, such magnitude-based decomposition is data-agnostic and does not explicitly account for target-relevant semantics, potentially leading to semantic misalignment. We propose COMPASS (COntextual Moment Prior Alignment for Subspace Separation), a data-aware subspace adaptation framework that uses a small unlabeled Semantic Proxy Set to estimate target activation statistics. COMPASS incorporates activation covariance into the decomposition of pre-trained weights, preserving target-relevant representations as a stable semantic reference while the residual adapter learns forgery-related variations. The proxy calibration requires no gradient-based optimization. Extensive experiments demonstrate strong generalization across cross-dataset, cross-method, joint cross-dataset-method, and open-world cross-generator evaluations, achieving state-of-the-art performance on both Deepfake and AIGI detection benchmarks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
