面向AI生成图像免训练检测的去偏重建框架
A Debiased Reconstruction-based Framework for Training-Free Detection of AI-Generated Images
对做视觉研究的人，这篇论文提供了一个可直接复用的免训练检测信号：用旋转与低通滤波增强来归一化LDM的图像级重建误差，抵消背景偏置；同时把潜变量级重建误差经旋转归一化后作为补充信号，二者统一为RDD分数，可在无检测训练数据时跨多种生成模型使用。
原文依据 we propose a novel image-level debiasing score function that cancels out background contribution by normalizing the reconstruction error on the augmented images
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论随着近期AI模型成功生成高分辨率逼真图像，检测图像是否由AI生成在社会层面也变得重要。由于生成模型多样，检测任务的训练数据往往不可得，因此免训练检测方法在实践上受到考虑。一种常见做法是利用潜扩散模型（LDM）的图像级重建误差。然而，我们发现该分数存在实例特定的偏置，在背景简单的图像中尤为明显。为此，我们提出一种新的图像级去偏评分函数，通过在与背景信息相似的增强图像上对重建误差进行归一化，抵消背景贡献。具体而言，我们表明旋转与低通滤波是有效的增强策略。为提升对更广泛生成模型的泛化能力，我们新探索了潜变量级重建误差作为额外的免训练信号。然而，我们观察到潜变量级分数同样受潜变量特定偏置影响。为缓解此问题，我们引入基于旋转潜变量归一化的旋转式潜变量级去偏分数。我们将上述分数统一为单一的统一去偏分数RDD，在多种生成模型上取得最优的免训练检测性能。此外，我们的框架对被测图像的损坏具有鲁棒性。
英文原文摘要 1500 字符
As recent AI models have successfully generated high-resolution photorealistic images, it has also been socially important to detect whether an image is generated by AI. Since training data for the detection task is often not available due to the diversity of generative models, training-free detection approaches have been practically considered. A common approach is to utilize the image-level reconstruction error from the latent diffusion model (LDM). However, we find this score suffers from instance-specific biases, particularly in images with simple backgrounds. To this end, we propose a novel image-level debiasing score function that cancels out background contribution by normalizing the reconstruction error on the augmented images with similar background information. To be specific, we show that rotation and low-pass filtering are effective augmentation strategies. To promote generalization to broader generative models, we newly explore latent-level reconstruction error as an additional training-free signal. However, we observe that the latent-level score also suffers to latent-specific bias. To mitigate this, we introduce a rotation-based latent-level debiasing score based on the normalization of the rotated latent. We unify the aforementioned scores into a single unified debiasing score, RDD, which achieves state-of-the-art training-free detection performance across diverse generative models. Furthermore, our framework can be robust to corruption of the examined images.