Deep Learning Logo Detection with Data Expansion by Synthesising Context

@article{Su2017DeepLL,
  title={Deep Learning Logo Detection with Data Expansion by Synthesising Context},
  author={Hang Su and Xiatian Zhu and Shaogang Gong},
  journal={2017 IEEE Winter Conference on Applications of Computer Vision (WACV)},
  year={2017},
  pages={530-539}
}
Logo detection in unconstrained images is challenging, particularly when only very sparse labelled training images are accessible due to high labelling costs. In this work, we describe a model training image synthesising method capable of improving significantly logo detection performance when only a handful of (e.g., 10) labelled training images captured in realistic context are available, avoiding extensive manual labelling costs. Specifically, we design a novel algorithm for generating… CONTINUE READING
Highly Cited
This paper has 18 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 29 times over the past 90 days. VIEW TWEETS

Citations

Publications citing this paper.

References

Publications referenced by this paper.
Showing 1-10 of 41 references

Top 10 Fashion Logos

  • I. Design
  • http:// inkbotdesign.com/top-10-fashion-logos/,
  • 2015
Highly Influential
4 Excerpts

The 50 Greatest Streetwear Brands

  • B. HUNDREDS
  • http://uk.complex.com/style/2011/06/ the-50…
  • 2011
Highly Influential
4 Excerpts

Similar Papers

Loading similar papers…