GroundingAnomaly: 基于空间的扩散用于少样本异常合成
GroundingAnomaly: Spatially-Grounded Diffusion for Few-Shot Anomaly Synthesis
AI总结：
本文提出GroundingAnomaly框架，通过空间条件模块和门控自注意力模块实现精准异常合成，提升少样本异常检测性能。
摘要：
视觉异常检测在工业质量控制中的性能常受限于真实异常样本的稀缺性。为此，异常合成技术被开发以扩大训练集并提升下游检测。然而，现有方法要么因修复不足导致整合不佳，要么无法提供准确的掩码。为解决这些问题，我们提出GroundingAnomaly，一种新的少样本异常图像生成框架。我们的框架引入了一个空间条件模块，利用像素级语义图来实现对合成异常的精确空间控制。此外，设计了一个门控自注意力模块，将条件标记注入到冻结的U-Net中，通过门控注意力层。这精心保留了预训练先验知识，同时确保稳定的少样本适应。在MVTec AD和VisA数据集上的广泛评估表明，GroundingAnomaly生成高质量的异常，并在多个下游任务中，包括异常检测、分割和实例级检测中实现了最先进的性能。
英文摘要：
The performance of visual anomaly inspection in industrial quality control is often constrained by the scarcity of real anomalous samples. Consequently, anomaly synthesis techniques have been developed to enlarge training sets and enhance downstream inspection. However, existing methods either suffer from poor integration caused by inpainting or fail to provide accurate masks. To address these limitations, we propose GroundingAnomaly, a novel few-shot anomaly image generation framework. Our framework introduces a Spatial Conditioning Module that leverages per-pixel semantic maps to enable precise spatial control over the synthesized anomalies. Furthermore, a Gated Self-Attention Module is designed to inject conditioning tokens into a frozen U-Net via gated attention layers. This carefully preserves pretrained priors while ensuring stable few-shot adaptation. Extensive evaluations on the MVTec AD and VisA datasets demonstrate that GroundingAnomaly generates high-quality anomalies and achieves state-of-the-art performance across multiple downstream tasks, including anomaly detection, segmentation, and instance-level detection.
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。
