CVA-GNN: Convolutional Vicinity Aggregation Graph Neural Network for Point Cloud Classification

Autor:	Scherer Rafal, Wojciechowski Adam, Najgebauer Patryk, Walczak Jakub
Rok vydání:	2021
Předmět:	Constraint (information theory) Salient Computer science business.industry Feature extraction Point cloud Neighbourhood (graph theory) Graph (abstract data type) Point (geometry) Pattern recognition Artificial intelligence business Convolution
Zdroj:	IJCNN
DOI:	10.1109/ijcnn52387.2021.9533545
Popis:	Point cloud classification is highly dependent on how points' features are extracted and aggregated. The graph-based feature extraction strategies are currently used. Not only point coordinates are taken into consideration but also neighbourhood pair-wise geometrical relations. A newly proposed Convolutional Vicinity Aggregation (CVA) module extends reference solutions with mutual geometrical point relations. Simultaneous convolution of points geometrical interrelations allows a network to retrieve salient features under the permutation-invariance constraint. The resulting hierarchical CVA-based architecture outperforms the state-of-the-art point cloud classification methods on the well-established ModelNet40 dataset. Additional analysis of the CVA module hyper-parameters was also provided in order to support its effectiveness.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::7516025edf97fecc3a49fdd8eb3a67a2 https://doi.org/10.1109/ijcnn52387.2021.9533545 Zobrazit plný text záznamu