Deep Learning Face Representation from Predicting 10,000 Classes

@article{Sun2014DeepLF,
  title={Deep Learning Face Representation from Predicting 10,000 Classes},
  author={Yi Sun and Xiaogang Wang and Xiaoou Tang},
  journal={2014 IEEE Conference on Computer Vision and Pattern Recognition},
  year={2014},
  pages={1891-1898}
}
This paper proposes to learn a set of high-level feature representations through deep learning, referred to as Deep hidden IDentity features (DeepID), for face verification. We argue that DeepID can be effectively learned through challenging multi-class face identification tasks, whilst they can be generalized to other tasks (such as verification) and new identities unseen in the training set. Moreover, the generalization capability of DeepID increases as more face classes are to be predicted… CONTINUE READING

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • Our method achieves 97.45% face verification accuracy on LFW using only weakly aligned faces, which is almost as good as human performance of 97.53%.
  • The transfer learning Joint Bayesian based on our DeepID features achieves 97.45% test accuracy on LFW, which is on par with the human-level performance of 97.53%.

Citations

Publications citing this paper.
SHOWING 1-10 OF 802 CITATIONS, ESTIMATED 99% COVERAGE

Patch strategy for deep face recognition

VIEW 7 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

Face Recognition via Deep Sparse Graph Neural Networks

VIEW 12 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Face recognition using both visible light image and near-infrared image and a deep network

  • CAAI Trans. Intell. Technol.
  • 2017
VIEW 6 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

A Comprehensive Study on Center Loss for Deep Face Recognition

  • International Journal of Computer Vision
  • 2018
VIEW 8 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2010
2019

CITATION STATISTICS

  • 84 Highly Influenced Citations

  • Averaged 174 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 37 REFERENCES

A Practical Transfer Learning Algorithm for Face Verification

  • 2013 IEEE International Conference on Computer Vision
  • 2013
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Blessing of Dimensionality: High-Dimensional Feature and Its Efficient Compression for Face Verification

  • 2013 IEEE Conference on Computer Vision and Pattern Recognition
  • 2013
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Learning hierarchical representations for face verification with convolutional deep belief networks

  • 2012 IEEE Conference on Computer Vision and Pattern Recognition
  • 2012
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Closing the gap to human - level performance in face verification

F. Porikli O. Tuzel, P. Meer
  • Proc . CVPR
  • 2014

DeepFace: Closing the Gap to Human-Level Performance in Face Verification

  • 2014 IEEE Conference on Computer Vision and Pattern Recognition
  • 2014
VIEW 2 EXCERPTS

Deep Convolutional Network Cascade for Facial Point Detection

  • 2013 IEEE Conference on Computer Vision and Pattern Recognition
  • 2013

Deep Learning Identity-Preserving Face Space

  • 2013 IEEE International Conference on Computer Vision
  • 2013
VIEW 1 EXCERPT