Open AccessDeformable convolutional networks for multi‐view 3D shape classification
Author(s) -
Ma Pengfei,
Ma Jie,
Wang Xujiao,
Yang Lichuang,
Wang Nannan
Publication year - 2018
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
eISSN - 1350-911X
pISSN - 0013-5194
DOI - 10.1049/el.2018.6851
Subject(s) - convolutional neural network , pooling , computer science , robustness (evolution) , artificial intelligence , pattern recognition (psychology) , transformation (genetics) , margin (machine learning) , layer (electronics) , geometric transformation , key (lock) , machine learning , image (mathematics) , biochemistry , chemistry , computer security , organic chemistry , gene
This Letter suggests a novel method for improving the robustness and the geometric transformation modelling capability in multi‐view convolutional networks (MVCNNs). First, the deformable convolutional networks are used to learn more details and features related to the geometric transformation which the standard convolutional neural networks cannot handle. Then a view‐pooling layer is specifically designed for combining the descriptors from multiple views as the final representations of the 3D shapes. The key idea is to insert the deformable convolutional layer between the input and convolutional layer, making it possible to solve deformable 3D shape classification problems, which was a challenging task for MVCNN framework. The proposed method achieves state‐of‐the‐art classification results on two subsets of the ModelNet dataset (ModelNet10 and ModelNet40) over previous methods by a significant margin.