paper-with-me

홈 › Papers

Autonomous Dimension Reduction by Flattening Deformation of Data Manifold under an Intrinsic Deforming Field

2021-10-21 · Xiaodong Zhuang

A new dimension reduction (DR) method for data sets is proposed by autonomous deforming of data manifolds. The deformation is guided by the proposed deforming vector field, which is defined by two kinds of virtual interactions between data points. The flattening of data manifold is achieved as an emergent behavior under the elastic and repelling interactions between data points, meanwhile the topological structure of the manifold is preserved. To overcome the uneven sampling (or "short-cut edge") problem, the soft neighborhood is proposed, in which the neighbor degree is defined and adaptive interactions between neighbor points is implemented. The proposed method provides a novel geometric viewpoint on dimension reduction. Experimental results prove the effectiveness of the proposed method in dimension reduction, and implicit feature of data sets may also be revealed.

📄 PDF Abstract BibTeX arXiv:2110.10938

Code (0)

등록된 구현이 없습니다.

Tasks

Dimensionality Reduction

Similar Papers 제목 키워드 기반

Modeling Human Strategy for Flattening Wrinkled Cloth Using Neural Networks

2024-08-19 · Nilay Kant, Ashrut Aryal, Rajiv Ranganathan, Ranjan Mukherjee 외

This paper explores a novel approach to model strategies for flattening wrinkled cloth learning from humans. A human participant study was conducted where the participants were presented with various wrinkle types and ta…

Robot Vision Architecture for Autonomous Clothes Manipulation

2016-10-18 · Li Sun, Gerardo Aragon-Camarasa, Simon Rogers, J. Paul Siebert

This paper presents a novel robot vision architecture for perceiving generic 3D clothes configurations. Our architecture is hierarchically structured, starting from low-level curvatures, across mid-level geometric shapes…

Kronecker Attention Networks

2020-07-16 · ICLR 2020 1 · Hongyang Gao, Zhengyang Wang, Shuiwang Ji

Attention operators have been applied on both 1-D data like texts and higher-order data such as images and videos. Use of attention operators on high-order data requires flattening of the spatial or spatial-temporal dime…

DEMEA: Deep Mesh Autoencoders for Non-Rigidly Deforming Objects

2019-05-24 · ECCV 2020 8 · Edgar Tretschk, Ayush Tewari, Michael Zollhöfer, Vladislav Golyanik 외

Mesh autoencoders are commonly used for dimensionality reduction, sampling and mesh modeling. We propose a general-purpose DEep MEsh Autoencoder (DEMEA) which adds a novel embedded deformation layer to a graph-convolutio…

3D ReconstructionDimensionality Reduction

Model reduction for the material point method via an implicit neural representation of the deformation map

2021-09-25 · Peter Yichen Chen, Maurizio M. Chiaramonte, Eitan Grinspun, Kevin Carlberg

This work proposes a model-reduction approach for the material point method on nonlinear manifolds. Our technique approximates the $\textit{kinematics}$ by approximating the deformation map using an implicit neural repre…

Super-Resolution