Visual Feature Encoding for GNNs on Road Networks
- URL: http://arxiv.org/abs/2203.01187v1
- Date: Wed, 2 Mar 2022 15:37:50 GMT
- Title: Visual Feature Encoding for GNNs on Road Networks
- Authors: Oliver Stromann, Alireza Razavi and Michael Felsberg
- Abstract summary: We propose an architecture that combines vision backbone networks with graph neural networks.
We perform a road type classification task on an Open Street Map road network through encoding of satellite imagery.
Our architecture further enables fine-tuning and a transfer-learning approach is evaluated by pretraining.
- Score: 14.274582421372308
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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.
Related papers
- Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch [72.26822499434446]
Auto-Train-Once (ATO) is an innovative network pruning algorithm designed to automatically reduce the computational and storage costs of DNNs.
We provide a comprehensive convergence analysis as well as extensive experiments, and the results show that our approach achieves state-of-the-art performance across various model architectures.
arXiv Detail & Related papers (2024-03-21T02:33:37Z) - Moving Object Proposals with Deep Learned Optical Flow for Video Object
Segmentation [1.551271936792451]
We propose a state of art architecture of neural networks to get the moving object proposals (MOP)
We first train an unsupervised convolutional neural network (UnFlow) to generate optical flow estimation.
Then we render the output of optical flow net to a fully convolutional SegNet model.
arXiv Detail & Related papers (2024-02-14T01:13:55Z) - Hierarchical Graph Pattern Understanding for Zero-Shot VOS [102.21052200245457]
This paper proposes a new hierarchical graph neural network (GNN) architecture for zero-shot video object segmentation (ZS-VOS)
Inspired by the strong ability of GNNs in capturing structural relations, HGPU innovatively leverages motion cues (ie, optical flow) to enhance the high-order representations from the neighbors of target frames.
arXiv Detail & Related papers (2023-12-15T04:13:21Z) - Set-based Neural Network Encoding [57.15855198512551]
We propose an approach to neural network weight encoding for generalization performance prediction.
Our approach is capable of encoding neural networks in a modelzoo of mixed architecture.
We introduce two new tasks for neural network generalization performance prediction: cross-dataset and cross-architecture.
arXiv Detail & Related papers (2023-05-26T04:34:28Z) - Online Hybrid Lightweight Representations Learning: Its Application to
Visual Tracking [42.49852446519412]
This paper presents a novel hybrid representation learning framework for streaming data.
An image frame in a video is modeled by an ensemble of two distinct deep neural networks.
We incorporate the hybrid representation technique into an online visual tracking task.
arXiv Detail & Related papers (2022-05-23T10:31:14Z) - All-optical graph representation learning using integrated diffractive
photonic computing units [51.15389025760809]
Photonic neural networks perform brain-inspired computations using photons instead of electrons.
We propose an all-optical graph representation learning architecture, termed diffractive graph neural network (DGNN)
We demonstrate the use of DGNN extracted features for node and graph-level classification tasks with benchmark databases and achieve superior performance.
arXiv Detail & Related papers (2022-04-23T02:29:48Z) - Learning to integrate vision data into road network data [14.86655504533083]
Road networks are the core infrastructure for connected and autonomous vehicles.
We propose to integrate remote sensing vision data into network data for improved embeddings with graph neural networks.
We achieve state-of-the-art performance on the OSM+Di Chuxing dataset on Chengdu, China.
arXiv Detail & Related papers (2021-12-20T15:38:49Z) - Self-Denoising Neural Networks for Few Shot Learning [66.38505903102373]
We present a new training scheme that adds noise at multiple stages of an existing neural architecture while simultaneously learning to be robust to this added noise.
This architecture, which we call a Self-Denoising Neural Network (SDNN), can be applied easily to most modern convolutional neural architectures.
arXiv Detail & Related papers (2021-10-26T03:28:36Z) - Segmentation of Roads in Satellite Images using specially modified U-Net
CNNs [0.0]
The aim of this paper is to build an image classifier for satellite images of urban scenes that identifies the portions of the images in which a road is located.
Unlike conventional computer vision algorithms, convolutional neural networks (CNNs) provide accurate and reliable results on this task.
arXiv Detail & Related papers (2021-09-29T19:08:32Z) - Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks [78.65792427542672]
Dynamic Graph Network (DG-Net) is a complete directed acyclic graph, where the nodes represent convolutional blocks and the edges represent connection paths.
Instead of using the same path of the network, DG-Net aggregates features dynamically in each node, which allows the network to have more representation ability.
arXiv Detail & Related papers (2020-10-02T16:50:26Z) - Embedded Encoder-Decoder in Convolutional Networks Towards Explainable
AI [0.0]
This paper proposes a new explainable convolutional neural network (XCNN) which represents important and driving visual features of stimuli.
The experimental results on the CIFAR-10, Tiny ImageNet, and MNIST datasets showed the success of our algorithm (XCNN) to make CNNs explainable.
arXiv Detail & Related papers (2020-06-19T15:49:39Z)
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.