.png){kind=icon}
返回
MapLayNet: map layout representation learning using weakly supervised structure-aware graph neural networks
.png){kind=icon}
OA
AI
DOI：10.1080/15230406.2025.2533316.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Openly accessible map images have become a valuable source for geographic information and cartographic design. Map layout becomes a natural leverage point to unlock fine-grained map information as it facilitates the expression of map content through the spatial coordination of map elements. Current layout studies focus on documents, user interfaces, and floor plans, leading to models that poorly recognize complex map layouts. Inspired by the strong performance of graph neural networks (GNNs) in modeling element-wise layout relationships, this paper proposes MapLayNet, a GNN-based model for map layout representation learning. The model introduces the structural features and proposes a dual-branch network architecture to enhance the model representation of complex map layouts at global and local scales. To ensure model generalization for diverse map layout designs, we employed a weakly supervised learning strategy and trained the model using a heuristic-based triplet loss of map layout similarity, along with a mutual information loss that effectively utilizes the dual-branch architecture. For model evaluation, MapLayNet has outperformed all baseline methods in similarity and stability by 3.2% and 10.3%, respectively, while showing better consistency against human evaluation on a map layout retrieval task. With the effective model design, the embedding learned by MapLayNet is capable of generating a concept hierarchy with compactness in lower-level layout patterns and partial-ordered concept relations in the higher-level layout abstraction. Potential applications such as map layout retrieval and design recommendation can be envisioned with the resulting interpretable and manipulable map layout embedding.
Keyword:
Map layout
GNN
structure-aware
layout similarity
ubiquitous map
embedding model
layout retrieval
期刊
IF:
2.4
论文数:
113
被引数:
1.5K
机构
引用论文
Graph Classification using Structural Attention.png)
Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
OAAI
Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningIF0
OAAI分享收藏Lee, J. T., Kim, H. U., Lee, C., & Kim, C. S. (2018). Photographic composition classification and dominant geometric element detection for outdoor scenes. Journal of Visual Communication and Image Representation, 55, 91–105. https://doi.org/10.1016/j.jvcir.2018.05.018 (Open in a new window)Web of Science ®(Open in a new window)Google ScholarLee, J. T., Kim, H. U., Lee, C., & Kim, C. S. (2018). 户外场景的摄影构图分类和主导几何元素检测. 视觉通信与图像表示杂志, 55, 91–105. https://doi.org/10.1016/j.jvcir.2018.05.018 (在新窗口中打开)Web of Science ®(在新窗口中打开)Google Scholar
IF0
PREAI
分享收藏Van Engelenburg, C. C., Khademi, S., & van Gemert, J. C. (2023). SSIG: A visually-guided graph edit distance for floor plan similarity. In J. Kosecka, J. Ponce, C. Schmid, & A. Zisserman (Eds.), Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 1573–1582). IEEE Computer Society and Computer Vision Foundation. https://doi.org/10.1109/ICCVW60793.2023.00172 (Open in a new window)Google ScholarVan Engelenburg, C. C., Khademi, S., & van Gemert, J. C. (2023)。SSIG：一种基于视觉引导的图编辑距离用于平面图相似性。载于J. Kosecka, J. Ponce, C. Schmid, & A. Zisserman（编），《IEEE/CVF国际计算机视觉会议论文集》（第1573–1582页）。IEEE计算机学会与计算机视觉基金会。https://doi.org/10.1109/ICCVW60793.2023.00172 (在新窗口中打开)Google Scholar
IF0
PREAI
分享收藏LayoutLM: Pre-training of Text and Layout for Document Image UnderstandingLayoutLM: 用于文档图像理解的文本和布局的预培训Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningOAAI
Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningIF0
OAAI分享收藏Eskenazi, S., Gomez-Krämer, P., & Ogier, J. M. (2015). The Delaunay document layout descriptor. In P. Genevès & C. Vanoirbeek (Eds.), Proceedings of the 2015 ACM Symposium on Document Engineering (pp. 167–175). Association for Computing Machinery. https://doi.org/10.1145/2682571.279705 (Open in a new window)Google ScholarEskenazi, S., Gomez-Krämer, P., & Ogier, J. M. (2015). Delaunay文档布局描述符。在P. Genevès & C. Vanoirbeek (编)，2015年ACM文档工程研讨会会议录（第167-175页）。计算 Machinery 协会。https://doi.org/10.1145/2682571.279705 (在新窗口中打开)Google Scholar
IF0
PREAI
分享收藏A graph convolutional neural network for classification of building patterns using spatial vector data基于空间矢量数据的图卷积神经网络建筑物模式分类OAAI
OAAI分享收藏分享收藏
查看更多内容