Deep Spatial Domain Generalization
- URL: http://arxiv.org/abs/2210.00729v1
- Date: Mon, 3 Oct 2022 06:16:20 GMT
- Title: Deep Spatial Domain Generalization
- Authors: Dazhou Yu, Guangji Bai, Yun Li, Liang Zhao
- Abstract summary: We develop the spatial graph neural network that handles spatial data as a graph and learns the spatial embedding on each node.
The proposed method infers the spatial embedding of an unseen location during the test phase and decodes the parameters of the downstream-task model directly on the target location.
- Score: 8.102110157532556
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Spatial autocorrelation and spatial heterogeneity widely exist in spatial
data, which make the traditional machine learning model perform badly. Spatial
domain generalization is a spatial extension of domain generalization, which
can generalize to unseen spatial domains in continuous 2D space. Specifically,
it learns a model under varying data distributions that generalizes to unseen
domains. Although tremendous success has been achieved in domain
generalization, there exist very few works on spatial domain generalization.
The advancement of this area is challenged by: 1) Difficulty in characterizing
spatial heterogeneity, and 2) Difficulty in obtaining predictive models for
unseen locations without training data. To address these challenges, this paper
proposes a generic framework for spatial domain generalization. Specifically,
We develop the spatial interpolation graph neural network that handles spatial
data as a graph and learns the spatial embedding on each node and their
relationships. The spatial interpolation graph neural network infers the
spatial embedding of an unseen location during the test phase. Then the spatial
embedding of the target location is used to decode the parameters of the
downstream-task model directly on the target location. Finally, extensive
experiments on thirteen real-world datasets demonstrate the proposed method's
strength.
Related papers
- ManiBox: Enhancing Spatial Grasping Generalization via Scalable Simulation Data Generation [37.73074657448699]
bfManiBox is a novel bounding-box-guided manipulation method built on a simulation-based teacher-student framework.
ManiBox demonstrates a marked improvement in spatial grasping generalization and adaptability to diverse objects and backgrounds.
arXiv Detail & Related papers (2024-11-04T07:05:02Z) - stMCDI: Masked Conditional Diffusion Model with Graph Neural Network for Spatial Transcriptomics Data Imputation [8.211887623977214]
We introduce textbfstMCDI, a novel conditional diffusion model for spatial transcriptomics data imputation.
It employs a denoising network trained using randomly masked data portions as guidance, with the unmasked data serving as conditions.
The results obtained from spatial transcriptomics datasets elucidate the performance of our methods relative to existing approaches.
arXiv Detail & Related papers (2024-03-16T09:06:38Z) - One-Shot Domain Adaptive and Generalizable Semantic Segmentation with
Class-Aware Cross-Domain Transformers [96.51828911883456]
Unsupervised sim-to-real domain adaptation (UDA) for semantic segmentation aims to improve the real-world test performance of a model trained on simulated data.
Traditional UDA often assumes that there are abundant unlabeled real-world data samples available during training for the adaptation.
We explore the one-shot unsupervised sim-to-real domain adaptation (OSUDA) and generalization problem, where only one real-world data sample is available.
arXiv Detail & Related papers (2022-12-14T15:54:15Z) - Intrinsic dimension estimation for discrete metrics [65.5438227932088]
In this letter we introduce an algorithm to infer the intrinsic dimension (ID) of datasets embedded in discrete spaces.
We demonstrate its accuracy on benchmark datasets, and we apply it to analyze a metagenomic dataset for species fingerprinting.
This suggests that evolutive pressure acts on a low-dimensional manifold despite the high-dimensionality of sequences' space.
arXiv Detail & Related papers (2022-07-20T06:38:36Z) - Localized Adversarial Domain Generalization [83.4195658745378]
Adversarial domain generalization is a popular approach to domain generalization.
We propose localized adversarial domain generalization with space compactness maintenance(LADG)
We conduct comprehensive experiments on the Wilds DG benchmark to validate our approach.
arXiv Detail & Related papers (2022-05-09T08:30:31Z) - Activation Regression for Continuous Domain Generalization with
Applications to Crop Classification [48.795866501365694]
Geographic variance in satellite imagery impacts the ability of machine learning models to generalise to new regions.
We model geographic generalisation in medium resolution Landsat-8 satellite imagery as a continuous domain adaptation problem.
We develop a dataset spatially distributed across the entire continental United States.
arXiv Detail & Related papers (2022-04-14T15:41:39Z) - Positional Encoder Graph Neural Networks for Geographic Data [1.840220263320992]
Graph neural networks (GNNs) provide a powerful and scalable solution for modeling continuous spatial data.
In this paper, we propose PE-GNN, a new framework that incorporates spatial context and correlation explicitly into the models.
arXiv Detail & Related papers (2021-11-19T10:41:49Z) - Batch Normalization Embeddings for Deep Domain Generalization [50.51405390150066]
Domain generalization aims at training machine learning models to perform robustly across different and unseen domains.
We show a significant increase in classification accuracy over current state-of-the-art techniques on popular domain generalization benchmarks.
arXiv Detail & Related papers (2020-11-25T12:02:57Z) - Auxiliary-task learning for geographic data with autoregressive
embeddings [1.4823143667165382]
We propose SXL, a method for embedding information on the autoregressive nature of spatial data directly into the learning process.
We utilize the local Moran's I, a popular measure of local spatial autocorrelation, to "nudge" the model to learn the direction and magnitude of local spatial effects.
We highlight how our method consistently improves the training of neural networks in unsupervised and supervised learning tasks.
arXiv Detail & Related papers (2020-06-18T12:16:08Z) - Spatial Attention Pyramid Network for Unsupervised Domain Adaptation [66.75008386980869]
Unsupervised domain adaptation is critical in various computer vision tasks.
We design a new spatial attention pyramid network for unsupervised domain adaptation.
Our method performs favorably against the state-of-the-art methods by a large margin.
arXiv Detail & Related papers (2020-03-29T09:03:23Z) - Multi-Scale Representation Learning for Spatial Feature Distributions
using Grid Cells [11.071527762096053]
We propose a representation learning model called Space2Vec to encode the absolute positions and spatial relationships of places.
Results show that because of its multi-scale representations, Space2Vec outperforms well-established ML approaches.
arXiv Detail & Related papers (2020-02-16T04:22:18Z)
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.