用图缩减保持细结构连通性，实现高分辨率无切片分割
SEMIR: Topology-Preserving Graph Minors for Thin-Structure Segmentation
- 用参数化图小波替代像素网格，保证细结构连接性
- 2100万像素图像可全分辨率推理，碎片化减少4.6倍以上
- 统一架构适配电力线、裂缝、车道线，性能超越专用模型
细结构分割（如1-3像素宽的输电线路、裂缝、航拍车道线）需保持连通性，但传统表示方式会破坏这种特性：切块会切断连续结构，常规超像素在分类前就将细目标合并进背景。拓扑感知损失虽能惩罚连接断裂，却无法恢复已被表示破坏的连通性。本文提出SEMIR框架，将像素网格替换为参数化图小波，其收缩映射在收缩准则下保持细结构连通性。该图小波将数百万像素压缩为数十至数百个边界对齐的超节点，支持全分辨率推理而无需切块，实验最高达2100万像素；轻量级GNN对简化图分类，精确映射将预测还原至像素级。单一流程——跨数据集使用相同架构、特征、损失和GNN超参——在TTPLA（电力线）、CrackSeg9k（路面裂缝）和SkyScapes Lane（航拍车道线）上，各项指标均达到或超过领域专用基线，且掩码碎片化程度较SLIC降低至少4.6倍。
原文摘要 · Abstract (English)
Thin-structure segmentation--power lines, cracks, lane markings at 1-3 pixel width--requires preserving connectivity that standard representations preclude: patching severs continuous structures and conventional superpixels merge thin targets into background before classification. Topology-aware losses penalize connectivity breaks at the objective level but cannot recover what the representation has already destroyed. We propose SEMIR, a framework that replaces the pixel lattice with a parameterized graph minor whose contraction map preserves thin-structure connectivity under the contraction criterion. The minor collapses millions of pixels into tens or hundreds of boundary-aligned supernodes, enabling full-resolution inference without patching at scales demonstrated up to 21 MP in this paper; a lightweight GNN classifies the reduced graph and an exact map lifts predictions to pixel resolution. One pipeline--identical architecture, features, loss, and GNN hyperparameters across all dataset--matches or exceeds domain-specific baselines on TTPLA (power lines), CrackSeg9k (pavement cracks), and SkyScapes Lane (aerial markings) on Dice, IoU, and Boundary F1 while reducing mask fragmentation by at least 4.6x relative to SLIC at matched inference.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。