HalluGen: 合成逼真且可控的幻觉以评估图像修复
HalluGen: Synthesizing Realistic and Controllable Hallucinations for Evaluating Image Restoration
AI总结：
HalluGen 通过合成逼真可控的幻觉，构建首个大规模幻觉数据集，用于评估图像修复中的幻觉检测与缓解。
摘要：
生成模型容易产生幻觉： plausible 但错误的结构在 ground truth 中不存在。这个问题在图像修复中尤为严重，特别是在医疗成像、工业检测和遥感等安全关键领域，此类错误会削弱可靠性与信任度。例如，在低场强 MRI 中，广泛用于资源有限的环境，修复模型对于增强低质量扫描至关重要，但幻觉可能导致严重诊断错误。进展受困于一个循环依赖：评估幻觉需要标注数据，但此类标签成本高且主观。我们引入 HalluGen，一种基于扩散的框架，能够合成逼真且可控类型的幻觉，位置和严重程度，产生在感知上逼真但语义上错误的输出（分割 IoU 从 0.86 降至 0.36）。使用 HalluGen，我们构建了首个大规模幻觉数据集，包含 4,350 张标注图像，源自 1,450 个脑部 MRI 图像用于低场强增强，使系统性评估幻觉检测和缓解成为可能。我们展示了其在两个应用中的效用：（1）基准测试图像质量度量并开发语义幻觉评估通过特征评估（SHAFE），一种基于特征的度量，通过软注意力池化提高对幻觉的敏感度，优于传统度量；（2）训练无参考幻觉检测器，使其能够泛化到真实的修复失败。共同，HalluGen 和其开放数据集建立了评估安全关键图像修复中幻觉的首个可扩展基础。
英文摘要：
Generative models are prone to hallucinations: plausible but incorrect structures absent in the ground truth. This issue is problematic in image restoration for safety-critical domains such as medical imaging, industrial inspection, and remote sensing, where such errors undermine reliability and trust. For example, in low-field MRI, widely used in resource-limited settings, restoration models are essential for enhancing low-quality scans, yet hallucinations can lead to serious diagnostic errors. Progress has been hindered by a circular dependency: evaluating hallucinations requires labeled data, yet such labels are costly and subjective. We introduce HalluGen, a diffusion-based framework that synthesizes realistic hallucinations with controllable type, location, and severity, producing perceptually realistic but semantically incorrect outputs (segmentation IoU drops from 0.86 to 0.36). Using HalluGen, we construct the first large-scale hallucination dataset comprising 4,350 annotated images derived from 1,450 brain MR images for low-field enhancement, enabling systematic evaluation of hallucination detection and mitigation. We demonstrate its utility in two applications: (1) benchmarking image quality metrics and developing Semantic Hallucination Assessment via Feature Evaluation (SHAFE), a feature-based metric with soft-attention pooling that improves hallucination sensitivity over traditional metrics; and (2) training reference-free hallucination detectors that generalize to real restoration failures. Together, HalluGen and its open dataset establish the first scalable foundation for evaluating hallucinations in safety-critical image restoration.
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。
