FAST: 前景感知扩散与加速采样轨迹用于面向分割的异常合成
FAST: Foreground-aware Diffusion with Accelerated Sampling Trajectory for Segmentation-oriented Anomaly Synthesis
AI总结：
FAST提出一种前景感知扩散框架，通过AIAS和FARM模块提升工业异常合成效率与质量，实现更可控的结构特定异常生成。
摘要：
工业异常分割严重依赖像素级标注，但现实中的异常往往稀缺、多样且标注成本高。面向分割的工业异常合成（SIAS）已作为一种有前景的替代方法出现；然而，现有方法在平衡采样效率和生成质量方面存在困难。此外，大多数方法对所有空间区域一视同仁，忽视了异常区域和背景区域之间显著的统计差异。这种统一处理阻碍了可控、结构特定的异常合成，以满足分割任务的需求。在本文中，我们提出了FAST，一种具有两个新模块的前景感知扩散框架：异常感知加速采样（AIAS）和前景感知重建模块（FARM）。AIAS是一种无需训练的采样算法，专门设计用于面向分割的工业异常合成，通过粗到细的聚合加速逆过程，并在10步内生成最先进的面向分割的异常。同时，FARM在每个采样步骤中自适应调整被遮蔽的前景区域内的异常感知噪声，保持局部异常信号在整个去噪轨迹中。在多个工业基准上的广泛实验表明，FAST在下游分割任务中始终优于现有异常合成方法。我们发布代码：https://github.com/Chhro123/fast-foreground-aware-anomaly-synthesis。
英文摘要：
Industrial anomaly segmentation relies heavily on pixel-level annotations, yet real-world anomalies are often scarce, diverse, and costly to label. Segmentation-oriented industrial anomaly synthesis (SIAS) has emerged as a promising alternative; however, existing methods struggle to balance sampling efficiency and generation quality. Moreover, most approaches treat all spatial regions uniformly, overlooking the distinct statistical differences between anomaly and background areas. This uniform treatment hinders the synthesis of controllable, structure-specific anomalies tailored for segmentation tasks. In this paper, we propose FAST, a foreground-aware diffusion framework featuring two novel modules: the Anomaly-Informed Accelerated Sampling (AIAS) and the Foreground-Aware Reconstruction Module (FARM). AIAS is a training-free sampling algorithm specifically designed for segmentation-oriented industrial anomaly synthesis, which accelerates the reverse process through coarse-to-fine aggregation and enables the synthesis of state-of-the-art segmentation-oriented anomalies in as few as 10 steps. Meanwhile, FARM adaptively adjusts the anomaly-aware noise within the masked foreground regions at each sampling step, preserving localized anomaly signals throughout the denoising trajectory. Extensive experiments on multiple industrial benchmarks demonstrate that FAST consistently outperforms existing anomaly synthesis methods in downstream segmentation tasks. We release the code at: https://github.com/Chhro123/fast-foreground-aware-anomaly-synthesis.
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。
