Skip to main content

VoCaM: Visualization oriented convolutional neural network acceleration on mobile system: Invited paper

Publication ,  Conference
Qin, Z; Xu, Z; Dong, Q; Chen, Y; Chen, X
Published in: IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD
December 13, 2017

Convolutional Neural Networks (CNNs) have been widely investigated as some of the most promising solution for various computer vision tasks. However, CNNs introduce massive computing overhead due to their complex network computing flow, resulting in significantly reduced applicability and performance, especially in the mobile devices. Various optimization schemes have been proposed mainly based on both model compression and stacked external computing resources. While these schemes have been proven effective, methods which take into account mobile-specific context-aware optimization approaches have been largely overlooked. One such opportunity is the feasible CNN computing flow simplification to the under-test objects with distinguish features, which can be efficiently pre-analyzed inside the mobile sensor system. Hence, we propose VoCaM, a visualization oriented CNN acceleration framework on mobile devices for image classification tasks. VoCaM takes advantage of the mobile camera system, where the comprehensive pre-analysis can be conducted to reveal the color composition of the under-test images without incurring any additional overhead. Also, the visualization analysis of VoCaM reveals that, certain color-specific filters may have very trivial result impact when the under-test images have mismatching primary color components. Then a set of approximate computing methods is applied to these insignificant filters to replace the intensive convolutional operation, and greatly accelerate the computing process. With ignorable overhead, VoCaM can significantly optimize the computation load of the convolutional layers, with very small impact on the overall classification accuracy.

Duke Scholars

Published In

IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD

DOI

ISSN

1092-3152

ISBN

9781538630938

Publication Date

December 13, 2017

Volume

2017-November

Start / End Page

835 / 840
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Qin, Z., Xu, Z., Dong, Q., Chen, Y., & Chen, X. (2017). VoCaM: Visualization oriented convolutional neural network acceleration on mobile system: Invited paper. In IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD (Vol. 2017-November, pp. 835–840). https://doi.org/10.1109/ICCAD.2017.8203864
Qin, Z., Z. Xu, Q. Dong, Y. Chen, and X. Chen. “VoCaM: Visualization oriented convolutional neural network acceleration on mobile system: Invited paper.” In IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD, 2017-November:835–40, 2017. https://doi.org/10.1109/ICCAD.2017.8203864.
Qin Z, Xu Z, Dong Q, Chen Y, Chen X. VoCaM: Visualization oriented convolutional neural network acceleration on mobile system: Invited paper. In: IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD. 2017. p. 835–40.
Qin, Z., et al. “VoCaM: Visualization oriented convolutional neural network acceleration on mobile system: Invited paper.” IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD, vol. 2017-November, 2017, pp. 835–40. Scopus, doi:10.1109/ICCAD.2017.8203864.
Qin Z, Xu Z, Dong Q, Chen Y, Chen X. VoCaM: Visualization oriented convolutional neural network acceleration on mobile system: Invited paper. IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD. 2017. p. 835–840.

Published In

IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD

DOI

ISSN

1092-3152

ISBN

9781538630938

Publication Date

December 13, 2017

Volume

2017-November

Start / End Page

835 / 840