Source Themes

A Hierarchical Spatial Transformer for Massive Point Samples in Continuous Space

We propose a novel hierarchical transformer architecture for massive point sample obervations in continuous space.

Wenchong He, Zhe Jiang, Tingsong Xiao, Zelin Xu, Shigang Chen, Ronald Fick, Miles Medina

A Hierarchical Spatial Transformer for Massive Point Samples in Continuous Space

Spatial Knowledge-Infused Hierarchical Learning: An Application in Flood Mapping on Earth Imagery

We propose a novel Spatial Knowledge-Infused Hierarchical Learning (SKI-HL) framework that iteratively infers sample labels within a multi-resolution hierarchy.

Zelin Xu, Tingsong Xiao, Wenchong He, Yu Wang, Zhe Jiang

Spatial Knowledge-Infused Hierarchical Learning: An Application in Flood Mapping on Earth Imagery

An Explainer for Temporal Graph Neural Networks

We propose the first explainer framework for temporal graph neural network.

Wenchong He, Minh N. Vu, Zhe Jiang, My Thai

An Explainer for Temporal Graph Neural Networks

Quantifying and Reducing Registration Uncertainty of Spatial Vector Labels on Earth Imagery

We propose uncertainty aware weakly supervised learning framework with registration error on Earth Imagery .

Wenchong He, Zhe Jiang, Marcus Kriby, Yiqun Xie, Xiaowei Jia, Da Yan, Yang Zhou

Quantifying and Reducing Registration Uncertainty of Spatial Vector Labels on Earth Imagery

Semi-Supervised Learning With the EM Algorithm: A Comparative Study Between Unstructured and Structured Prediction

we conduct a comparative study between unstructured and structured methods in EM-based semi-supervised learning.

Wenchong He, Zhe Jiang

Semi-Supervised Learning With the EM Algorithm: A Comparative Study Between Unstructured and Structured Prediction

Earth Imagery Segmentation on Terrain Surface with Limited Training Labels: A Semi-supervised Approach based on Physics-Guided Graph Co-Training

We propose a novel framework that explicitly models the topological skeleton of a terrain surface with a contour tree from computational topology, which is guided by the physical constraint (e.g., water flow direction on terrains).

Wenchong He, Zhe Jiang, Arpan Man Sainju, Da Yan, Yang Zhou

Earth Imagery Segmentation on Terrain Surface with Limited Training Labels: A Semi-supervised Approach based on Physics-Guided Graph Co-Training

Weakly Supervised Spatial Deep Learning for Earth Image Segmentation Based on Imperfect Polyline Labels

We proposes a weakly supervised learning framework to simultaneously update deep learning model parameters and infer hidden true vector label locations.

Zhe Jiang, Wenchong He, Marcus Kriby, Arpan Man Sainju, Shaowen Wang, Lawrence V. Stanislawski, Ethan J. Shavers, E. Lynn Usery

Weakly Supervised Spatial Deep Learning for Earth Image Segmentation Based on Imperfect Polyline Labels

CurvaNet: Geometric Deep Learning based on Directional Curvature for 3D Shape Analysis

We proposes a novel geometric deep learning model called CurvaNet that integrates differential geometry with graph neural networks.

Wenchong He, Zhe Jiang, Chengming Zhang, Arpan Man Sainju

CurvaNet: Geometric Deep Learning based on Directional Curvature for 3D Shape Analysis

Weakly Supervised Spatial Deep Learning based on Imperfect Vector Labels with Registration Errors

We proposes a spatial learning framework based on Expectation-Maximization that iteratively updates deep neural network parameters while inferring true vector label locations.

Zhe Jiang, Wenchong He, Marcus Kirby, Sultan Asiri, Da Yan

Weakly Supervised Spatial Deep Learning based on Imperfect Vector Labels with Registration Errors

Deep neural network for 3D surface segmentation based on contour tree hierarchy

we propose to represent surface topological structure by a contour tree skeleton, which is a polytree capturing the evolution of surface contours at different elevation levels. We further design a graph neural network based on the contour tree hierarchy to model surface topological structure at different spatial scales.

Wenchong He, Arpan Man Sainju, Zhe Jiang, Da Yan

Deep neural network for 3D surface segmentation based on contour tree hierarchy