BV-CNNs: Binary Volumetric Convolutional Networks for 3D Object Recognition

Chao Ma, Wei An, Yinjie Lei and Yulan Guo

Abstract

Though 3D convolutional neural networks (CNNs) have achieved impressive performance for object recognition, they still face challenges in computational and memory cost. In this paper, we propose binary volumetric convolutional neural networks (namely, BV-CNNs) for efficient 3D object recognition. Specially, it transforms the inputs and weights in the network to binary values through binary transformation, then the floating-point arithmetic convolutions are replaced with bitwise operations to reduce the computational and memory cost. Three binary volumetric CNNs are introduced from the traditional CNNs using our BV-CNN approach.

Session

Posters

Files

PDF iconPaper (PDF)

DOI

10.5244/C.31.148
https://dx.doi.org/10.5244/C.31.148

Citation

Chao Ma, Wei An, Yinjie Lei and Yulan Guo. BV-CNNs: Binary Volumetric Convolutional Networks for 3D Object Recognition. In T.K. Kim, S. Zafeiriou, G. Brostow and K. Mikolajczyk, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 148.1-148.12. BMVA Press, September 2017.

Bibtex

            @inproceedings{BMVC2017_148,
                title={BV-CNNs: Binary Volumetric Convolutional Networks for 3D Object Recognition},
                author={Chao Ma, Wei An, Yinjie Lei and Yulan Guo},
                year={2017},
                month={September},
                pages={148.1-148.12},
                articleno={148},
                numpages={12},
                booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
                publisher={BMVA Press},
                editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
                doi={10.5244/C.31.148},
                isbn={1-901725-60-X},
                url={https://dx.doi.org/10.5244/C.31.148}
            }