P$^3$-SAM：具有感知并行提示的SAM用于少样本带钢表面缺陷分割
P$^3$-SAM: SAM with Perceptual Parallel Prompt for Few-Shot Strip Steel Surface Defect Segmentation
- Shandong University（山东大学）
- Alibaba International Digital Commercial Group（阿里巴巴国际数字商业集团）
- Lingnan University（岭南大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对带钢表面缺陷少样本分割中低对比度、光照不均等挑战，提出感知并行提示框架P$^3$-SAM，通过感知优化编码和并行提示生成策略，在三个基准上取得最优性能，mIoU提升12%。
AI中文摘要：
带钢表面缺陷的少样本语义分割（FSS）与自然场景相比提出了显著不同的挑战。与自然图像不同，S$^3$D任务表现出独特的特点，包括低局部对比度、不均匀照明和复杂的细粒度纹理模式。尽管最近基于Segment Anything Model（SAM）的方法通过利用SAM强大的预训练表示在自然图像的FSS中显示出前景，但S$^3$D图像的这些独特工业特性导致直接将SAM应用于工业缺陷场景时性能下降。在本文中，我们提出了一种新颖的感知并行提示（P$^3$）框架，该框架赋能SAM，创建了P$^3$-SAM模型，通过两个核心策略来解决这些挑战。首先，我们开发了一种感知优化编码（POE）策略，该策略增强了局部对比度并保留了S$^3$D分割的关键纹理细节。其次，我们引入了并行提示生成器（PPG）策略，该策略同时生成语义和空间提示，为SAM的解码器在不同图像上提供全面指导。在三个少样本S$^3$D基准上的大量实验表明，P$^3$-SAM实现了最先进的性能，在Surface Defects-4i数据集上mIoU特别显著提高了12.00%。
英文摘要：
Few-shot semantic segmentation (FSS) of strip steel surface defects (S$^3$D) has posed significant challenges distinct from natural scenes. Unlike natural images, S$^3$D task exhibits unique characteristics including low local contrast, uneven illumination, and complex fine-grained texture patterns. Although recent methods based on Segment Anything Model (SAM) have shown promise in FSS on natural images by leveraging SAM's powerful pre-trained representations, these unique industrial characteristics of S$^3$D images lead to performance drop when directly applying SAM to industrial defect scenarios. In this paper, we propose a novel Perceptual Parallel Prompt (P$^3$) framework that empowers SAM, creating the P$^3$-SAM model to address these challenges through two core strategies. First, we develop a Perceptual-Optimized Encoding (POE) strategy that enhances local contrast and preserves critical texture details for S$^3$D segmentation. Second, we introduce the Parallel Prompt Generator (PPG) strategy that simultaneously generates both semantic and spatial prompts, enabling comprehensive guidance for SAM's decoder across varying images. Extensive experiments on three few-shot S$^3$D benchmarks demonstrate that P$^3$-SAM achieves state-of-the-art performance, with particularly notable improvements of 12.00% in mIoU on Surface Defects-4i dataset.
