Frankenstein: Learning Deep Face Representations Using Small Data

@article{Hu2017FrankensteinLD,
  title={Frankenstein: Learning Deep Face Representations Using Small Data},
  author={Guosheng Hu and Xiaojiang Peng and Yongxin Yang and Timothy M. Hospedales and Jakob Verbeek},
  journal={IEEE Transactions on Image Processing},
  year={2017},
  volume={27},
  pages={293-303}
}
Deep convolutional neural networks have recently proven extremely effective for difficult face recognition problems in uncontrolled settings. To train such networks, very large training sets are needed with millions of labeled images. For some applications, such as near-infrared (NIR) face recognition, such large training data sets are not publicly available and difficult to collect. In this paper, we propose a method to generate very large training data sets of synthetic images by compositing… CONTINUE READING
Recent Discussions
This paper has been referenced on Twitter 31 times over the past 90 days. VIEW TWEETS
9 Citations
65 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-9 of 9 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 65 references

Similar Papers

Loading similar papers…