Layoutgmn: Neural Graph Matching For Structural Layout Similarity

Abstract

We present a deep neural network to predict structural similarity between 2D layouts by leveraging Graph Matching Networks (GMN). Our network, coined LayoutGMN, learns the layout metric via neural graph matching, using an attention-based GMN designed under a triplet network setting. To train our network, we utilize weak labels obtained by pixel-wise Intersection-over-Union (IoUs) to define the triplet loss. Importantly, LayoutGMN is built with a structural bias which can effectively compensate for the lack of structure awareness in IoUs. We demonstrate this on two prominent forms of layouts, viz., floorplans and UI designs, via retrieval experiments on large-scale datasets. In particular, retrieval results by our network better match human judgement of structural layout similarity compared to both IoUs and other baselines including a state-of-the-art method based on graph neural networks and image convolution. In addition, LayoutGMN is the first deep model to offer both metric learning

Stats

• citations17
• S2 citations—
• github stars0
• HF likes0
• heat score9.41
• arxiv keypatil2020layoutgmn

Related papers

• SEGMN: A Structure-enhanced Graph Matching Network For Graph Similarity Learning (2024)2.26
• Sub-gmn: The Neural Subgraph Matching Network Model (2021)6.34
• Towards Interpretable Deep Metric Learning With Structural Matching (2021)15.87
• Hierarchical Graph Matching Network For Graph Similarity Computation (2020)0.00
• SSIG: A Visually-guided Graph Edit Distance For Floor Plan Similarity (2023)5.24
• Multi-view Dense Image Matching With Similarity Learning And Geometry Priors (2025)0.00
• Hierarchical Metric Learning And Matching For 2D And 3D Geometric Correspondences (2018)11.39
• Graph2region: Efficient Graph Similarity Learning With Structure And Scale Restoration (2025)0.00