NCDL: A Framework for Deep Learning on non-Cartesian Lattices
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
NCDL: A Framework for Deep Learning on non-Cartesian Lattices
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 LearningLearning to Discover and Detect Objects
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+1Morphological adjunctions represented by matrices in max-plus algebra for signal and image processing
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
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+2A Cartesian-3j Framework for Machine Learning Interatomic Potentials
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)…