Visual Feature Encoding for GNNs on Road Networks
In this work, we present a novel approach to learning an encoding of visual features into graph neural networks with the application on road network data. We propose an architecture that combines state-of-the-art vision backbone networks with graph neural networks. More specifically, we perform a road type classification task on an Open Street Map road network through encoding of satellite imagery using various ResNet architectures. Our architecture further enables fine-tuning and a transfer-learning approach is evaluated by pretraining on the NWPU-RESISC45 image classification dataset for remote sensing and comparing them to purely ImageNet-pretrained ResNet models as visual feature encoders. The results show not only that the visual feature encoders are superior to low-level visual features, but also that the fine-tuning of the visual feature encoder to a general remote sensing dataset such as NWPU-RESISC45 can further improve the performance of a GNN on a machine learning task like road type classification.
Code (0)
등록된 구현이 없습니다.
Tasks
Classificationimage-classificationImage ClassificationTransfer LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
BRAVE: Broadening the visual encoding of vision-language models
Vision-language models (VLMs) are typically composed of a vision encoder, e.g. CLIP, and a language model (LM) that interprets the encoded features to solve downstream tasks. Despite remarkable progress, VLMs are subject…
HallucinationLanguage ModellingVisual Question Answering (VQA)Improving Subgraph-GNNs via Edge-Level Ego-Network Encodings
We present a novel edge-level ego-network encoding for learning on graphs that can boost Message Passing Graph Neural Networks (MP-GNNs) by providing additional node and edge features or extending message-passing formats…
Graph ClassificationGraph RegressionH$^3$GNNs: Harmonizing Heterophily and Homophily in GNNs via Joint Structural Node Encoding and Self-Supervised Learning
Graph Neural Networks (GNNs) struggle to balance heterophily and homophily in representation learning, a challenge further amplified in self-supervised settings. We propose H$^3$GNNs, an end-to-end self-supervised learni…
Representation LearningSelf-Supervised LearningFeature Construction Using Network Control Theory and Rank Encoding for Graph Machine Learning
In this article, we utilize the concept of average controllability in graphs, along with a novel rank encoding method, to enhance the performance of Graph Neural Networks (GNNs) in social network classification tasks. GN…
Graphtester: Exploring Theoretical Boundaries of GNNs on Graph Datasets
Graph Neural Networks (GNNs) have emerged as a powerful tool for learning from graph-structured data. However, even state-of-the-art architectures have limitations on what structures they can distinguish, imposing theore…