Learned and Hand-crafted Feature Fusion in Unit Ball for 3D Object Classification

Sameera Ramasinghe, Salman Khan, Nick Barnes

Abstract

Convolution is an effective technique that can be used to obtain abstract feature representations using hierarchical layers in deep networks. However, performing convolution in non-Euclidean topological spaces such as the unit ball (B3) is still an under-explored problem. In this paper, we propose a light-weight experimental architecture for 3D object classification, that operates in B3. The proposed network utilizes both hand-crafted and learned features, and uses capsules in the penultimate layer to disentangle 3D shape features through pose and view equivariance. It simultaneously maintains an intrinsic co-ordinate frame, where mutual relationships between object parts are preserved. Furthermore, we show that the optimal view angles for extracting patterns from 3D objects depend on its shape and achieve compelling results with a relatively shallow network, compared to the state-of-the-art.

Download


Paper Citation


in Harvard Style

Ramasinghe S., Khan S. and Barnes N. (2020). Learned and Hand-crafted Feature Fusion in Unit Ball for 3D Object Classification.In Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-397-1, pages 115-125. DOI: 10.5220/0009344801150125


in Bibtex Style

@conference{icpram20,
author={Sameera Ramasinghe and Salman Khan and Nick Barnes},
title={Learned and Hand-crafted Feature Fusion in Unit Ball for 3D Object Classification},
booktitle={Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2020},
pages={115-125},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009344801150125},
isbn={978-989-758-397-1},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Learned and Hand-crafted Feature Fusion in Unit Ball for 3D Object Classification
SN - 978-989-758-397-1
AU - Ramasinghe S.
AU - Khan S.
AU - Barnes N.
PY - 2020
SP - 115
EP - 125
DO - 10.5220/0009344801150125