Skip to content

A Tensorflow implementation of "A Light CNN for Deep Face Representation with Noisy Labels"

Notifications You must be signed in to change notification settings

yxu0611/Tensorflow-implementation-of-LCNN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

71 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Light CNN for Deep Face Recognition, in Tensorflow

A Tensorflow implementation of A Light CNN for Deep Face Representation with Noisy Labels from the paper by Xiang Wu

Updates

  • Jan 9, 2018
    • Add cleaned training list 10K and 70K.
  • Sep 20, 2017
    • Add model and evaluted code.
    • Add training code.
  • Sep 19, 2017
    • The repository was built.

Datasets

  • Training data
    • Download face dataset MS-Celeb-1M (Aligned).
    • All face images are RGB images and resize to 122x144
    • Download MS-Celeb-1M cleaned image_list 10K, 70K
  • Testing data

Training

  • Add

Evaluation

Performance

The Light CNN performance on lfw 6,000 pairs.

Model traing data method Acc 100% - EER TPR@FAR=1% TPR@FAR=0.1% TPR@FAR=0
LightCNN-29 (Wu Xiang) 70K/- Softmax - 99.40% 99.43% 98.67% 95.70%
LightCNN-29 (Tensorflow) 10K/- Softmax 98.36% 98.2% 97.73% 92.26% 60.53%
LightCNN-29 (Tensorflow) 10K/- Softmax+L2+PCA 98.76% 98.66%   98.36%     97%   79.33%
LightCNN-29 (Tensorflow) 10K/- Softmax+L2+PCA+[b] 98.95% 98.8%   98.76%     97.16%   83.36%
LightCNN-29 (Tensorflow) 10K/- Softmax_enforce+L2+PCA+[b] 99.01% 98.96%   98.96%     95.83%   90.23%
Model traing data method Acc 100% - EER TPR@FAR=1% TPR@FAR=0.1% TPR@FAR=0
LightCNN-29 (Wu Xiang) 70K/- Softmax - 99.40% 99.43% 98.67% 95.70%
LightCNN-29 (Tensorflow) 70K/- Softmax_enforce+L2+PCA 99.18% 98.9%   98.86%     97.9%   94.03%
LightCNN-29 (Tensorflow) 70K/- Softmax_enforce+L2+PCA+[a] 99.48% 99.43%   99.56%     98.26%   94.53%

Some improved solutions:

  • [a] It can be further improved by manaully aligned these images which are mis-algined in LFW
  • [b] It can be further improved by doing mutiple-crop, e.g. 25 crops for per image
  • [c] It can be further improved by ensemble different models
  • [d] It can be further improved by adding metric learning method for similarity caculation

Referencs

About

A Tensorflow implementation of "A Light CNN for Deep Face Representation with Noisy Labels"

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published