paper-with-me

Papers

Spatio-Temporal driven Attention Graph Neural Network with Block Adjacency matrix (STAG-NN-BA)

2023-03-25 · U. Nazir, W. Islam, M. Taj

Despite the recent advances in deep neural networks, standard convolutional kernels limit the applications of these networks to the Euclidean domain only. Considering the geodesic nature of the measurement of the earth's surface, remote sensing is one such area that can benefit from non-Euclidean and spherical domains. For this purpose, we propose a novel Graph Neural Network architecture for spatial and spatio-temporal classification using satellite imagery. We propose a hybrid attention method to learn the relative importance of irregular neighbors in remote sensing data. Instead of classifying each pixel, we propose a method based on Simple Linear Iterative Clustering (SLIC) image segmentation and Graph Attention GAT. The superpixels obtained from SLIC become the nodes of our Graph Convolution Network (GCN). We then construct a region adjacency graph (RAG) where each superpixel is connected to every other adjacent superpixel in the image, enabling information to propagate globally. Finally, we propose a Spatially driven Attention Graph Neural Network (SAG-NN) to classify each RAG. We also propose an extension to our SAG-NN for spatio-temporal data. Unlike regular grids of pixels in images, superpixels are irregular in nature and cannot be used to create spatio-temporal graphs. We introduce temporal bias by combining unconnected RAGs from each image into one supergraph. This is achieved by introducing block adjacency matrices resulting in novel Spatio-Temporal driven Attention Graph Neural Network with Block Adjacency matrix (STAG-NN-BA). We evaluate our proposed methods on two remote sensing datasets namely Asia14 and C2D2. In comparison with both non-graph and graph-based approaches our SAG-NN and STAG-NN-BA achieved superior accuracy on all the datasets while incurring less computation cost. The code and dataset will be made public via our GitHub repository.

📄 PDF Abstract BibTeX arXiv:2303.14322

Code (0)

등록된 구현이 없습니다.

Tasks

Graph AttentionGraph Neural NetworkImage SegmentationRAGSemantic SegmentationSuperpixels

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Graph Neural Network 설명 없음
Weight Decay 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Towards Scalable and Structured Spatiotemporal Forecasting

2025-09-10 · Hongyi Chen, Xiucheng Li, Xinyang Chen, Jing Li 외 arxiv

In this paper, we propose a novel Spatial Balance Attention block for spatiotemporal forecasting. To strike a balance between obeying spatial proximity and capturing global correlation, we partition the spatial graph int…

Enhancing Topological Dependencies in Spatio-Temporal Graphs with Cycle Message Passing Blocks

2024-01-29 · Minho Lee, Yun Young Choi, Sun Woo Park, Seunghwan Lee 외

Graph Neural Networks (GNNs) and Transformer-based models have been increasingly adopted to learn the complex vector representations of spatio-temporal graphs, capturing intricate spatio-temporal dependencies crucial for…

Spatio-Temporal ForecastingTime Series PredictionTraffic Prediction

Ada-TransGNN: An Air Quality Prediction Model Based On Adaptive Graph Convolutional Networks

2025-08-25 · Dan Wang, Feng Jiang, Zhanquan Wang arxiv

Accurate air quality prediction is becoming increasingly important in the environmental field. To address issues such as low prediction accuracy and slow real-time updates in existing models, which lead to lagging predic…

Graph structure learning

ST-GRIT: Spatio-Temporal Graph Transformer For Internal Ice Layer Thickness Prediction

2025-07-10 · Zesheng Liu, Maryam Rahnemoonfar arxiv

Understanding the thickness and variability of internal ice layers in radar imagery is crucial for monitoring snow accumulation, assessing ice dynamics, and reducing uncertainties in climate models. Radar sensors, capabl…

Graph Learning

STAMImputer: Spatio-Temporal Attention MoE for Traffic Data Imputation

2025-06-09 · Yiming Wang, Hao Peng, Senzhang Wang, Haohua Du 외

Traffic data imputation is fundamentally important to support various applications in intelligent transportation systems such as traffic flow prediction. However, existing time-to-space sequential methods often fail to e…

Graph AttentionImputationMixture-of-ExpertsTraffic Data Imputation