NormFace: L2 HyperSphere Embedding for Face Verification

http://www.cs.jhu.edu/~alanlab/Pubs17/wang2017normface.pdf

* It is 98.13% on Light CNN's project page. After applying the mirror face trick, it becomes 98.41%.

1. My Caffe (https://github.com/happynear/caffe-windows/tree/ms). It also works on Linux. Anyway, if you want to use your own Caffe, please transplant the inner_product_layer, inner_distance_layer, normalize_layer, general_contrastive_layer, flip_layer and accuracy_layer to your Caffe. Since there are too many layers to transplant, I suggest you to use my Caffe directly:)
2. Matlab to draw some figures.
3. GPU with CUDA support.
4. MTCNN face and facial landmark detector(https://github.com/kpzhang93/MTCNN_face_detection_alignment).
5. Baseline model such as Center Face or Light CNN or your own model trained by softmax loss. I don't know whether my loss helps or not if your model is trained by other loss functions. You may have a try. I believe it will be effective if there is no normalization term in your model.

1. The dataset used in this paper is CASIA-Webface. Note that there are 3 identities overlap between CASIA-Webface and LFW. They are 0166921, 1056413 and 1193098. For fair evaluation, it is recommended to remove them from CAISA-Webface.
2. Align all face images using MTCNN. The script can be found in my another github repository.
3. Replace the final inner-product layer and softmax layer with layers defined in scaled_cosine_softmax.prototxt or normalized_Euclidean_contrastive.prototxt.
4. Fine-tune the network based on the original model using a small learning rate, say 0.001 or 0.0001.

Evaluation codes are in my another github repository. Please refer to the second paragraph of the Update section.

A trick called mirror face is used during extracting the features. A sample code is in ./prototxt/example_of_mirror_face.prototxt.

About the mirror face: See ./MirrorFace.md

About the histogram feature for video face verification: Details are in ./YTF.

Light CNN B model(98.78%): Google Drive or Baidu Yun.

ps: I used to get a model of 98.8%, but I lost it....

Center Face (ResNet-27) model(99.21%): Google Drive or Baidu Yun.

This code is distributed under MIT LICENSE. The released models are only allowed for non-commercial use.

If you find my paper or the codes useful in your research, please cite

@inproceedings{wang2017normface,
  title={NormFace: L2 Hypersphere Embedding for Face Verification},
  author={Wang, Feng and Xiang, Xiang and Cheng, Jian and Yuille, Alan L.},
  booktitle={Proceedings of the 25th ACM international conference on Multimedia},
  year={2017},
  organization={ACM},
  doi = {https://doi.org/10.1145/3123266.3123359}
}

Feng Wang [feng.wff(at)gmail.com], please replace (at) with @.