paper-with-me

Papers

NCDL: A Framework for Deep Learning on non-Cartesian Lattices

2023-09-21 · NeurIPS 2023 11

The use of non-Cartesian grids is a niche but important topic in sub-fields of the numerical sciences such as simulation and scientific visualization. However, non-Cartesian approaches are virtually unexplored in machine learning. This is likely due to the difficulties in the representation of data on non-Cartesian domains and the lack of support for standard machine learning operations on non-Cartesian data. This paper proposes a new data structure called the lattice tensor which generalizes traditional tensor spatio-temporal operations to lattice tensors, enabling the use of standard machine learning algorithms on non-Cartesian data. However, data need not reside on a non-Cartesian structure, we use non-Dyadic downsampling schemes to bring Cartesian data into a non-Cartesian space for further processing. We introduce a software library that implements the lattice tensor container (with some common machine learning operations), and demonstrate its effectiveness. Our method provides a general framework for machine learning on non-Cartesian domains, addressing the challenges mentioned above and filling a gap in the current literature.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Learning

Methods 이 논문이 사용한 방법론

Library 설명 없음

Similar Papers 제목 키워드 기반

NCDL: A Framework for Deep Learning on non-Cartesian Lattices

2023-09-21

The use of non-Cartesian grids is a niche but important topic in sub-fields of the numerical sciences such as simulation and scientific visualization. However, non-Cartesian approaches are virtually unexplored in machine…

Deep Learning

Learning to Discover and Detect Objects

2022-10-19 · Vladimir Fomenko, Ismail Elezi, Deva Ramanan, Laura Leal-Taixé 외

We tackle the problem of novel class discovery and localization (NCDL). In this setting, we assume a source dataset with supervision for only some object classes. Instances of other classes need to be discovered, classif…

Novel Class DiscoveryNovel Object DetectionObjectObject Detection+1

Morphological adjunctions represented by matrices in max-plus algebra for signal and image processing

2022-07-28 · Samy Blusseau, Santiago Velasco-Forero, Jesus Angulo, Isabelle Bloch

In discrete signal and image processing, many dilations and erosions can be written as the max-plus and min-plus product of a matrix on a vector. Previous studies considered operators on symmetrical, unbounded complete l…

Debiased Novel Category Discovering and Localization

2024-02-29 · Juexiao Feng, Yuhong Yang, Yanchun Xie, Yaqian Li 외

In recent years, object detection in deep learning has experienced rapid development. However, most existing object detection models perform well only on closed-set datasets, ignoring a large number of potential objects …

Contrastive LearningNovel Class DiscoveryObjectobject-detection+2

A Cartesian-3j Framework for Machine Learning Interatomic Potentials

2025-12-18 · Zemin Xu, Chenyu Wu, Wenbo Xie, P. Hu arxiv

Machine learning interatomic potentials (MLIPs) have brought substantial gains in the extrapolation capability in computational chemistry. However, most equivariant models are typically built with spherical tensors (STs)…