paper-with-me

Papers

Generalizing the Convolution Operator to extend CNNs to Irregular Domains

2016-06-03 · Jean-Charles Vialatte, Vincent Gripon, Grégoire Mercier

Convolutional Neural Networks (CNNs) have become the state-of-the-art in supervised learning vision tasks. Their convolutional filters are of paramount importance for they allow to learn patterns while disregarding their locations in input images. When facing highly irregular domains, generalized convolutional operators based on an underlying graph structure have been proposed. However, these operators do not exactly match standard ones on grid graphs, and introduce unwanted additional invariance (e.g. with regards to rotations). We propose a novel approach to generalize CNNs to irregular domains using weight sharing and graph-based operators. Using experiments, we show that these models resemble CNNs on regular domains and offer better performance than multilayer perceptrons on distorded ones.

📄 PDF Abstract BibTeX arXiv:1606.01166

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Convolutional neural networks on irregular domains based on approximate vertex-domain translations

2017-10-27 · Bastien Pasdeloup, Vincent Gripon, Jean-Charles Vialatte, Dominique Pastor 외

We propose a generalization of convolutional neural networks (CNNs) to irregular domains, through the use of a translation operator on a graph structure. In regular settings such as images, convolutional layers are desig…

Translation

MeshConv3D: Efficient convolution and pooling operators for triangular 3D meshes

2025-01-07 · Germain Bregeon, Marius Preda, Radu Ispas, Titus Zaharia

Convolutional neural networks (CNNs) have been pivotal in various 2D image analysis tasks, including computer vision, image indexing and retrieval or semantic classification. Extending CNNs to 3D data such as point cloud…

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

2016-06-30 · NeurIPS 2016 12 · Michaël Defferrard, Xavier Bresson, Pierre Vandergheynst

In this work, we are interested in generalizing convolutional neural networks (CNNs) from low-dimensional regular grids, where image, video and speech are represented, to high-dimensional irregular domains, such as socia…

Node ClassificationSkeleton Based Action Recognition

Graph Based Convolutional Neural Network

2016-09-28 · Michael Edwards, Xianghua Xie

The benefit of localized features within the regular domain has given rise to the use of Convolutional Neural Networks (CNNs) in machine learning, with great proficiency in the image classification. The use of CNNs becom…

BIG-bench Machine LearningGeneral Classificationimage-classificationImage Classification

Generalizing the Convolution Operator in Convolutional Neural Networks

2017-07-14 · Kamaledin Ghiasi-Shirazi

Convolutional neural networks have become a main tool for solving many machine vision and machine learning problems. A major element of these networks is the convolution operator which essentially computes the inner prod…