Accelerating Computation of Exemplar-SVM by Binary Approximation based on Matrix Decomposition
Takato Kurokawa, Yuji Yamauchi, Mitsuru Ambai, Takayoshi YAMASHITA and Hironobu Fujiyoshi
Abstract
The Exemplar-SVM (E-SVM) is a learning method based on exemplar that uses only
one positive sample and a substantial number of negative samples. In the detection stage,
it is possible to detect the location of the target object and estimate the attribute by transferring the attribute of the nearest exemplar. The use of E-SVM classifiers leads to very
high computational cost because it is necessary to compute the inner products of weight
vectors for multiple classifiers and an input feature vector. For accelerating the computation of E-SVM, we propose binary approximation based on matrix decomposition.
First, we stack the E-SVM’s weight vectors as a matrix. Then, we decompose the matrix
into common binary basis vectors and real-valued coefficient vectors for computing the
approximated inner products by logical operation. We also introduce early rejection by
cascade structure classifier into the proposed method.
Session
Posters
Files
Paper (PDF)
Supplementary (PDF)
DOI
10.5244/C.31.141
https://dx.doi.org/10.5244/C.31.141
Citation
Takato Kurokawa, Yuji Yamauchi, Mitsuru Ambai, Takayoshi YAMASHITA and Hironobu Fujiyoshi. Accelerating Computation of Exemplar-SVM by Binary Approximation based on Matrix Decomposition. In T.K. Kim, S. Zafeiriou, G. Brostow and K. Mikolajczyk, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 141.1-141.12. BMVA Press, September 2017.
Bibtex
@inproceedings{BMVC2017_141,
title={Accelerating Computation of Exemplar-SVM by Binary Approximation based on Matrix Decomposition},
author={Takato Kurokawa, Yuji Yamauchi, Mitsuru Ambai, Takayoshi YAMASHITA and Hironobu Fujiyoshi},
year={2017},
month={September},
pages={141.1-141.12},
articleno={141},
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.31.141},
isbn={1-901725-60-X},
url={https://dx.doi.org/10.5244/C.31.141}
}