通过分析采样过程中的图像相似性轨迹，仅用少量数据就能识别扩散模型生成图的缺陷。
Similarity Trajectories: Linking Sampling Process to Artifacts in Diffusion-Generated Images
- 利用采样过程中连续步骤间图像相似性的变化轨迹作为特征
- 仅用680张标注图像即实现72.35%的误检率准确率
- 适合需要轻量级、低资源的图像质量检测场景
图像伪影检测算法对修正扩散模型输出至关重要。然而，由于伪影形式多样，现有方法需大量标注数据训练，限制了其可扩展性和效率。本文发现，扩散模型采样过程中连续时间步间去噪图像的相似性与生成图像中伪影的严重程度相关。基于此，提出相似性轨迹（Similarity Trajectory）来刻画采样过程与图像伪影之间的关联。利用仅680张标注图像（仅为先前工作数据量的0.1%），训练分类器预测伪影存在。在平衡数据集上进行10折验证，分类器准确率达72.35%，证实了相似性轨迹与伪影出现之间的关联。该方法可在极小训练数据下区分含伪影与自然图像。
原文摘要 · Abstract (English)
Artifact detection algorithms are crucial to correcting the output generated by diffusion models. However, because of the variety of artifact forms, existing methods require substantial annotated data for training. This requirement limits their scalability and efficiency, which restricts their wide application. This paper shows that the similarity of denoised images between consecutive time steps during the sampling process is related to the severity of artifacts in images generated by diffusion models. Building on this observation, we introduce the concept of Similarity Trajectory to characterize the sampling process and its correlation with the image artifacts presented. Using an annotated data set of 680 images, which is only 0.1% of the amount of data used in the prior work, we trained a classifier on these trajectories to predict the presence of artifacts in images. By performing 10-fold validation testing on the balanced annotated data set, the classifier can achieve an accuracy of 72.35%, highlighting the connection between the Similarity Trajectory and the occurrence of artifacts. This approach enables differentiation between artifact-exhibiting and natural-looking images using limited training data.
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。