VisAdj：从节点-链接图像学习邻接矩阵
VisAdj: Learning Adjacency Matrices from Node-Link Images
浏览论文内容
中文总结 AI 辅助
针对从节点-链接图像学习邻接矩阵的问题，提出VisAdj框架，通过注意力稀疏邻居采样器与线图变换器实现拓扑感知的邻接预测，在合成图、道路网络和船舶图像上性能优于现有基线。
中文摘要 AI 辅助
从节点-链接图像学习邻接矩阵是从视觉观测中恢复结构化图信息的基础问题。现有方法通常依赖基于固定KNN的启发式方法进行候选边选择，且无法捕捉边之间的依赖关系。为克服这些局限，我们提出VisAdj，这是一个面向拓扑感知的邻接预测新框架。VisAdj引入注意力稀疏邻居采样器，自适应选择高召回率的候选节点对集合，并使用线图变换器执行联合边推理，该变换器将候选边视为token，显式建模关联边之间的依赖关系。在合成图、道路网络和船舶图像上的大量实验表明，VisAdj始终以明显优势优于现有基线方法。
英文摘要
Learning adjacency matrices from node-link images is a fundamental problem for recovering structured graph information from visual observations. Existing methods typically rely on fixed KNN-based heuristics for candidate edge selection and fail to capture dependencies among edges. To overcome these limitations, we propose VisAdj, a new framework for topology-aware adjacency prediction. VisAdj introduces an attention-sparse neighbor sampler to adaptively select a high-recall set of candidate node pairs and performs joint edge inference using a line-graph transformer that treats candidate edges as tokens and explicitly models dependencies among incident edges. Extensive experiments on synthetic graphs, road networks, and vessel images demonstrate that VisAdj consistently outperforms existing baselines by clear margins.
发表机构
- University of Delaware（特拉华大学）
机构由 AI 辅助整理，请以论文原文为准。
