提出DCA方法，检测冻结视觉模型在单张图像内语义区域的一致性。
Dimensional Coactivation for Representational Consistency in Frozen Vision Foundation Models
- 通过特征维度共激活度量图像内部语义区域的一致性
- 在深伪检测任务中达到0.9106（CelebDF-v2）和0.9289（DFD）AUC
- 验证了原始幅值信息对一致性判断的关键作用，适合模型可解释性研究
冻结的视觉基础模型不仅提取特征，还通过学习到的坐标系组织图像。我们探讨该坐标系在单个输入内部是否保持一致，从而引出表征一致性：即模型是否在样本的语义子区域间保持一致表示。本文提出维度共激活（DCA），一种针对每个特征维度的内在一致性测量工具。DCA通过考察相同特征维度在不同语义区域是否同时激活来评估一致性。与传统相似性度量不同，DCA刻意避免中心化、L2归一化和全维度耦合，因为这些操作适用于跨模型或分布比较，却不适合固定坐标系下的单样本场景，此时原始幅值携带关键信号。深伪检测提供了自然的验证任务：合成人脸可能复现合理的眼、鼻、口，但破坏真实人脸中的结构关联。使用冻结的DINOv3特征，DCA在CelebDF-v2上实现0.9106 AUC，DFD上达0.9289（FF++ c23跨数据集迁移）。消融实验进一步验证：重新引入中心化使CelebDF-v2 AUC降至0.459，L2归一化降至0.862，跨维度耦合降至0.478。替换为FaRL后，CelebDF-v2 AUC降至0.582。结果表明DCA依赖于稳定的维度坐标系，而非仅区域提取能力。因此，DCA可作为衡量冻结基础模型内部表征一致性的工具，深伪检测为其首个验证任务。
原文摘要 · Abstract (English)
Frozen vision foundation models do not merely extract features; they organize images through a learned coordinate system. We ask whether that coordinate system remains internally coherent within a single input. This leads to Representational Consistency: the study of whether a frozen foundation model represents one sample coherently across its semantic subregions. We introduce Dimensional Coactivation (DCA), a per-dimension instrument for measuring this coherence. DCA compares semantic regions by asking whether the same feature dimensions coactivate across them. Unlike classical similarity measures, it deliberately avoids centering, L2 normalization, and full Gram coupling. These operations are useful when comparing different models or distributions, but they are mismatched to the intra-sample setting, where the coordinate system is fixed and raw magnitude carries signal. Deepfake detection provides a natural validation task. Synthetic faces may reproduce plausible eyes, noses, and mouths while breaking the representational structure that links those regions in real faces. Using frozen DINOv3 features, DCA exposes this break: an eyes-mouth-nose fingerprint achieves 0.9106 AUC on CelebDF-v2 and 0.9289 on DFD under FF++ c23 cross-dataset transfer. The design is also sharply validated by ablation: reintroducing centering collapses CelebDF-v2 AUC to 0.459, L2 normalization reduces it to 0.862, and cross-dimension coupling reduces it to 0.478. Finally, replacing DINOv3 with FaRL collapses CelebDF-v2 AUC to 0.582. DCA therefore depends on a stable per-dimension coordinate system, not on region extraction alone. These results position DCA as an instrument for measuring intra-sample representational coherence in frozen foundation models, with deepfake detection as the first validation task.
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。