SPDCN：用于钢表面缺陷分割的基于条带的可变形卷积网络

中文摘要 AI 辅助

钢表面缺陷分割对工业质量检测至关重要，但现有方法因标准卷积的各向同性感受野和刚性采样网格难以适应不规则缺陷边界，在处理如裂纹和划痕等细长、各向异性缺陷时存在困难。为解决这些限制，我们提出了基于条带的可变形卷积网络预测器（SPDCN），有两个关键创新。模糊增强多尺度上下文模块（FMCM）采用分组多分支卷积和直觉模糊通道注意力机制来自适应捕获不同缺陷大小的多尺度上下文信息。自适应方向感知可变形卷积（ADADC）用解耦的水平和垂直条带卷积取代传统偏移预测器，使可变形采样网格能各向异性地与细长缺陷的主方向对齐。在公共钢表面缺陷基准上的大量实验表明，SPDCN始终优于现有方法，在NEU - Seg上仅用354万个参数就实现了89.60%的平均交并比。源代码可在指定网址公开获取。

英文摘要

Steel surface defect segmentation is critical for industrial quality inspection, yet existing methods struggle with elongated, anisotropic defects such as cracks and scratches due to the isotropic receptive fields of standard convolutions and rigid sampling grids that cannot adapt to irregular defect boundaries. To address these limitations, we propose Strip-based Predictor for Deformable Convolutional Networks (SPDCN) with two key innovations. The \textbf{Fuzzy-enhanced Multi-scale Context Module (FMCM)} employs group-wise multi-branch convolutions with an intuitionistic fuzzy channel attention mechanism to adaptively capture multi-scale contextual information across varying defect sizes. The \textbf{Adaptive Direction-Aware Deformable Convolution (ADADC)} replaces the conventional offset predictor with decoupled horizontal and vertical strip convolutions, enabling the deformable sampling grid to anisotropically align with the principal orientation of elongated defects. Extensive experiments on public steel surface defect benchmarks demonstrate that SPDCN consistently outperforms state-of-the-art methods, achieving 89.60\% mIoU on NEU-Seg with only 3.54M parameters. The source code is publicly available at https://github.com/DWlzm .

发表机构

• School of Artificial Intelligence, Jiangxi Normal University（江西师范大学人工智能学院）
• Jiangxi Provincial Key Laboratory of Intelligent Information Processing and Affective Computing（江西省智能信息处理与情感计算重点实验室）

机构由 AI 辅助整理，请以论文原文为准。