FLASH：工业异常检测中合成异常生成的“一次生成，多次合成”框架
FLASH: A "Generate Once, Synthesize Many" Framework for Synthetic Anomaly Generation in Industrial Anomaly Detection
浏览论文内容
中文总结 AI 辅助
FLASH提出“一次生成，多次合成”框架，解耦缺陷生成与异常合成，利用VLM和图像生成模型提取可复用缺陷补丁，结合OBS和MRSP高效合成多样异常，在MVTec AD 2上以78.1% F1接近真实异常性能，速度提升11.95倍。
中文摘要 AI 辅助
合成异常生成有助于在真实缺陷稀缺或不可用时扩充工业异常数据集。现有方法处于两个极端：程序化方法速度快但难以表示复杂异常，而生成式方法能产生多样缺陷但需要昂贵的逐样本生成。我们提出FLASH，一个在“一次生成，多次合成”范式下将缺陷生成与异常合成解耦的框架。仅给定正常图像，FLASH利用视觉语言模型（VLM）引导和图像生成模型产生少量缺陷图像，从中提取、验证并存储可复用的缺陷补丁。在异常图像合成中，目标边界抑制（OBS）首先识别宿主图像中可能的显著前景目标区域，而多分辨率光谱金字塔（MRSP）噪声生成多样且尺寸可控的掩码，决定缺陷位置和空间范围。随后，通过定位缺陷区域、采样尺寸可控的放置掩码，并将检索到的缺陷无缝融合到新的无缺陷图像上，无需进一步图像生成，即可合成大量多样的合成异常图像集。在MVTec AD 2数据集上的实验表明，FLASH生成的异常几乎弥合了与真实缺陷的校准差距，图像级F1达到78.1%，而真实异常上限为83.6%，且在程序化和生成式替代方法中提供了最一致的跨检测器校准迁移。此外，FLASH合成异常的速度比逐样本生成方法快11.95倍以上。
英文摘要
Synthetic anomaly generation helps expand industrial anomaly datasets when real defects are scarce or unavailable. Existing approaches lie at two extremes: procedural approaches are fast but struggle to represent complex anomalies, while generative approaches produce diverse defects but require costly per-sample generation. We present FLASH, a framework that decouples defect generation from anomaly synthesis under a ``generate once, synthesize many'' paradigm. Given only normal images, FLASH uses Vision-Language Model (VLM) guidance and an image-generation model to produce a small set of defect images, from which it extracts, validates, and banks reusable defect patches. For synthesis of anomalous images, Object Boundary Suppression (OBS) first identifies the probable foreground object-aware region of the host image, while Multi-Resolution Spectral Pyramid (MRSP) noise generates diverse, size-controllable masks that determine the defect location and spatial extent. It then composes a large and diverse synthetic anomalous image set by localizing the defect region, sampling size-controllable placement masks and seamlessly blending retrieved defects onto new defect-free images without further need for image generation. Experiments on the MVTec AD 2 dataset show that FLASH-generated anomalies nearly close the calibration gap on real defects, reaching 78.1% image-level F1 against an 83.6% real-anomaly upper bound and providing the most consistent calibration transfer across detectors among procedural and generative alternatives. Moreover, FLASH synthesizes anomalies more than 11.95x faster than per-sample generative approaches.
发表机构
- Silicon University（硅谷大学）
- Intel（英特尔）
机构由 AI 辅助整理，请以论文原文为准。
