Towards General-Purpose Representation Learning of Polygonal Geometries

• URL: http://arxiv.org/abs/2209.15458v1
• Date: Thu, 29 Sep 2022 15:59:23 GMT
• Title: Towards General-Purpose Representation Learning of Polygonal Geometries
• Authors: Gengchen Mai, Chiyu Jiang, Weiwei Sun, Rui Zhu, Yao Xuan, Ling Cai, Krzysztof Janowicz, Stefano Ermon, Ni Lao
• Abstract summary: We develop a general-purpose polygon encoding model, which can encode a polygonal geometry into an embedding space. We conduct experiments on two tasks: 1) shape classification based on MNIST; 2) spatial relation prediction based on two new datasets - DBSR-46K and DBSR-cplx46K. Our results show that NUFTspec and ResNet1D outperform multiple existing baselines with significant margins.
• Score: 62.34832826705641
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Neural network representation learning for spatial data is a common need for geographic artificial intelligence (GeoAI) problems. In recent years, many advancements have been made in representation learning for points, polylines, and networks, whereas little progress has been made for polygons, especially complex polygonal geometries. In this work, we focus on developing a general-purpose polygon encoding model, which can encode a polygonal geometry (with or without holes, single or multipolygons) into an embedding space. The result embeddings can be leveraged directly (or finetuned) for downstream tasks such as shape classification, spatial relation prediction, and so on. To achieve model generalizability guarantees, we identify a few desirable properties: loop origin invariance, trivial vertex invariance, part permutation invariance, and topology awareness. We explore two different designs for the encoder: one derives all representations in the spatial domain; the other leverages spectral domain representations. For the spatial domain approach, we propose ResNet1D, a 1D CNN-based polygon encoder, which uses circular padding to achieve loop origin invariance on simple polygons. For the spectral domain approach, we develop NUFTspec based on Non-Uniform Fourier Transformation (NUFT), which naturally satisfies all the desired properties. We conduct experiments on two tasks: 1) shape classification based on MNIST; 2) spatial relation prediction based on two new datasets - DBSR-46K and DBSR-cplx46K. Our results show that NUFTspec and ResNet1D outperform multiple existing baselines with significant margins. While ResNet1D suffers from model performance degradation after shape-invariance geometry modifications, NUFTspec is very robust to these modifications due to the nature of the NUFT.

Related papers

• Poly2Vec: Polymorphic Encoding of Geospatial Objects for Spatial Reasoning with Deep Neural Networks [6.1981153537308336]
  Poly2Vec is an encoding framework that unifies the modeling of different geospatial objects. We leverage the power of the 2D Fourier transform to encode useful spatial properties, such as shape and location. This unified approach eliminates the need to develop and train separate models for each distinct spatial type.
  arXiv  Detail & Related papers  (2024-08-27T06:28:35Z)
• PolygonGNN: Representation Learning for Polygonal Geometries with Heterogeneous Visibility Graph [8.971120205703887]
  We introduce a framework specifically designed for learning representations of polygonal geometries, particularly multipolygons. To enhance computational efficiency and minimize graph redundancy, we implement a heterogeneous spanning tree sampling method. We also introduce Multipolygon-GNN, a novel model tailored to leverage the spatial and semantic heterogeneity inherent in the visibility graph.
  arXiv  Detail & Related papers  (2024-06-30T16:07:49Z)
• Geometry-Aware Network for Domain Adaptive Semantic Segmentation [64.00345743710653]
  We propose a novel Geometry-Aware Network for Domain Adaptation (GANDA) to shrink the domain gaps. We exploit 3D topology on the point clouds generated from RGB-D images for coordinate-color disentanglement and pseudo-labels refinement in the target domain. Our model outperforms state-of-the-arts on GTA5->Cityscapes and SYNTHIA->Cityscapes.
  arXiv  Detail & Related papers  (2022-12-02T00:48:44Z)
• Revisiting Transformation Invariant Geometric Deep Learning: Are Initial Representations All You Need? [80.86819657126041]
  We show that transformation-invariant and distance-preserving initial representations are sufficient to achieve transformation invariance. Specifically, we realize transformation-invariant and distance-preserving initial point representations by modifying multi-dimensional scaling. We prove that TinvNN can strictly guarantee transformation invariance, being general and flexible enough to be combined with the existing neural networks.
  arXiv  Detail & Related papers  (2021-12-23T03:52:33Z)
• PolyWorld: Polygonal Building Extraction with Graph Neural Networks in Satellite Images [10.661430927191205]
  This paper introduces PolyWorld, a neural network that directly extracts building vertices from an image and connects them correctly to create precise polygons. PolyWorld significantly outperforms the state-of-the-art in building polygonization.
  arXiv  Detail & Related papers  (2021-11-30T15:23:17Z)
• PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representation [51.147664305955495]
  3D shape representation and its processing have substantial effects on 3D shape recognition. We propose a deep neural network-based method (PolyNet) and a specific polygon representation (PolyShape) Our experiments demonstrate the strength and the advantages of PolyNet on both 3D shape classification and retrieval tasks.
  arXiv  Detail & Related papers  (2021-10-15T06:45:59Z)
• ResNet-LDDMM: Advancing the LDDMM Framework Using Deep Residual Networks [86.37110868126548]
  In this work, we make use of deep residual neural networks to solve the non-stationary ODE (flow equation) based on a Euler's discretization scheme. We illustrate these ideas on diverse registration problems of 3D shapes under complex topology-preserving transformations.
  arXiv  Detail & Related papers  (2021-02-16T04:07:13Z)
• PUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsampling [103.09504572409449]
  We propose a novel deep neural network based method, called PUGeo-Net, to generate uniform dense point clouds. Thanks to its geometry-centric nature, PUGeo-Net works well for both CAD models with sharp features and scanned models with rich geometric details.
  arXiv  Detail & Related papers  (2020-02-24T14:13:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.