paper-with-me

Papers

Geometric Neural Operators (GNPs) for Data-Driven Deep Learning of Non-Euclidean Operators

2024-04-16 · Blaine Quackenbush, Paul J. Atzberger

We introduce Geometric Neural Operators (GNPs) for accounting for geometric contributions in data-driven deep learning of operators. We show how GNPs can be used (i) to estimate geometric properties, such as the metric and curvatures, (ii) to approximate Partial Differential Equations (PDEs) on manifolds, (iii) learn solution maps for Laplace-Beltrami (LB) operators, and (iv) to solve Bayesian inverse problems for identifying manifold shapes. The methods allow for handling geometries of general shape including point-cloud representations. The developed GNPs provide approaches for incorporating the roles of geometry in data-driven learning of operators.

📄 PDF Abstract BibTeX arXiv:2404.10843

Code (1)

atzberg/geo_neural_op pytorch

Similar Papers 제목 키워드 기반

Transferable Foundation Models for Geometric Tasks on Point Cloud Representations: Geometric Neural Operators

2025-03-06 · Blaine Quackenbush, Paul J. Atzberger

We introduce methods for obtaining pretrained Geometric Neural Operators (GNPs) that can serve as basal foundation models for use in obtaining geometric features. These can be used within data processing pipelines for ma…

Geometric Neural Operators via Lie Group-Constrained Latent Dynamics

2026-02-18 · Jiaquan Zhang, Fachrina Dewi Puspitasari, Songbo Zhang, Yibei Liu 외 arxiv

Neural operators offer an effective framework for learning solutions of partial differential equations for many physical systems in a resolution-invariant and data-driven manner. Existing neural operators, however, often…

Anchor-Free Person Search

2021-03-22 · CVPR 2021 1 · Yichao Yan, Jinpeng Li, Jie Qin, Song Bai 외

Person search aims to simultaneously localize and identify a query person from realistic, uncropped images, which can be regarded as the unified task of pedestrian detection and person re-identification (re-id). Most exi…

Pedestrian DetectionPerson Re-IdentificationPerson Search

Log-Euclidean Signatures for Intrinsic Distances Between Unaligned Datasets

2022-02-03 · Tal Shnitzer, Mikhail Yurochkin, Kristjan Greenewald, Justin Solomon

The need for efficiently comparing and representing datasets with unknown alignment spans various fields, from model analysis and comparison in machine learning to trend discovery in collections of medical datasets. We u…

BiQUE: Biquaternionic Embeddings of Knowledge Graphs

2021-09-29 · EMNLP 2021 11 · Jia Guo, Stanley Kok

Knowledge graph embeddings (KGEs) compactly encode multi-relational knowledge graphs (KGs). Existing KGE models rely on geometric operations to model relational patterns. Euclidean (circular) rotation is useful for model…

Knowledge Graph EmbeddingsKnowledge GraphsTranslation