ML Anthology

Offline 1000-Class Classification on a Smartphone

Yoshiyuki Kawano, Keiji Yanai
CVPRW 2014 pp. 193-194
doi:10.1109/CVPRW.2014.35 /cvprw/2014/kawano2014cvprw-offline/

Abstract

In this demo, we propose an offline large-scale image classification system on a smartphone. The proposed system can classify 1000-class objects in the ILSVRC2012 dataset in 0.270 seconds. To implement a 1000-class object classification system, we compress the weight vectors of linear classifiers, which leads only slight performance loss.

CVPRW Semantic Scholar

Cite

Text

Kawano and Yanai. "Offline 1000-Class Classification on a Smartphone." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2014. doi:10.1109/CVPRW.2014.35

Markdown

[Kawano and Yanai. "Offline 1000-Class Classification on a Smartphone." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2014.](https://mlanthology.org/cvprw/2014/kawano2014cvprw-offline/) doi:10.1109/CVPRW.2014.35

BibTeX

@inproceedings{kawano2014cvprw-offline,
  title     = {{Offline 1000-Class Classification on a Smartphone}},
  author    = {Kawano, Yoshiyuki and Yanai, Keiji},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2014},
  pages     = {193-194},
  doi       = {10.1109/CVPRW.2014.35},
  url       = {https://mlanthology.org/cvprw/2014/kawano2014cvprw-offline/}
}