Premium
Learning class‐specific descriptors for deformable shapes using localized spectral convolutional networks
Author(s) -
Boscaini D.,
Masci J.,
Melzi S.,
Bronstein M. M.,
Castellani U.,
Vandergheynst P.
Publication year - 2015
Publication title -
computer graphics forum
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.578
H-Index - 120
eISSN - 1467-8659
pISSN - 0167-7055
DOI - 10.1111/cgf.12693
Subject(s) - generalization , computer science , convolutional neural network , artificial intelligence , pattern recognition (psychology) , fourier transform , euclidean geometry , class (philosophy) , algorithm , mathematics , mathematical analysis , geometry
In this paper, we propose a generalization of convolutional neural networks (CNN) to non‐Euclidean domains for the analysis of deformable shapes. Our construction is based on localized frequency analysis (a generalization of the windowed Fourier transform to manifolds) that is used to extract the local behavior of some dense intrinsic descriptor, roughly acting as an analogy to patches in images. The resulting local frequency representations are then passed through a bank of filters whose coefficient are determined by a learning procedure minimizing a task‐specific cost. Our approach generalizes several previous methods such as HKS, WKS, spectral CNN, and GPS embeddings. Experimental results show that the proposed approach allows learning class‐specific shape descriptors significantly outperforming recent state‐of‐the‐art methods on standard benchmarks.