欢迎来到Cross-Pose LFW (CPLFW)数据库，它是Labeled Faces in the Wild (LFW)的翻新版，是无约束人脸验证的事实标准测试平台。

野生标签脸（LFW）数据库已被广泛用作无约束人脸验证的基准，由于大数据驱动的机器学习方法，该数据库的性能几乎接近100%。然而，我们认为这一准确性可能过于乐观。除了不同的光照、遮挡和表情，交叉姿势的人脸是人脸识别的另一个挑战，但LFW并没有对其给予太多的关注。因此，我们构建了一个跨姿势的LFW（CPLFW），它特意搜索并选择了3000个有姿势差异的正脸对，以增加类内差异的姿势变化。同时，还选择了具有相同性别和种族的阴性对，以减少阳性/阴性对之间属性差异的影响。我们在新数据库中评估了几种深度学习方法。与LFW上的准确率相比，CPLFW上的准确率下降了大约15%-20%。构建CPLFW基准的背后有三个动机，如下。

1、建立一个相对更难的数据库来评估真实世界人脸验证的性能，这样就可以充分证明几种人脸验证方法的有效性。

2、继续深入研究LFW，更真实地考虑姿态的类内变化，并促进无约束情况下的跨姿态人脸验证研究。CPLFW的挑战在于强调姿势差异，以进一步扩大类内差异。此外，还特意选择了负数对以避免不同的性别或种族。CPLFW同时考虑了大的类内方差和小的类间方差。

3、保持数据大小，提供 "相同/不同 "基准的人脸验证协议和LFW中的相同身份，所以人们可以很容易地应用CPLFW来评估人脸验证的性能。

• Comparison with LFW
  

• Pose distribution comparison
  

   

  According to the figures, the yaw distribution of images in CPLFW is more average. Also, pose difference of most positive pairs in LFW is less than 40 degrees while that of most positive pairs in CPLFW is larger. This confirms the existence of pose variation in intra-class variance of CPLFW.

  Positive pairs comparison
  

   

  CPLFW is collected by crowdsourcing efforts to seek the pictures of people in LFW with pose difference as large as possible on the Internet. Compared to LFW, the positive pairs in CPLFW contain obvious pose difference.

  Compared to LFW, the negative pairs in CPLFW have same gender and race, which reduces the influence of attribute difference between positive pairs and negative pairs in face verification.

We dedicate to maintain the protocols, dataset size, and the identities in each fold of LFW database in order to encourage fair and meaningful comparisons. You can find more information about standard LFW protocol in Labeled Faces in the Wild (LFW).

We expect CPLFW could promote algorithms to make reliable verification judgement, and close the large gap between the  reported performance on benchmarks and performance on real world tasks.

• Reference

• Please cite as:
  
  
  T. Zheng and W. Deng, Cross-pose LFW: A database for studying cross-pose face recognition in unconstrained environments, Beijing University of Posts and Telecommunications, Technical Report 18-01, February, 2018.[pdf]
  
  BibTeX entry:
  

  @TechReport{CPLFWTech,
    author =       {T. Zheng and W. Deng},
    title =        {Cross-pose LFW: A database for studying cross-pose face recognition in unconstrained environments},
    institution =  {Beijing University of Posts and Telecommunications},
    year =         {2018},
    number =       {18-01},
    month =        {February}}
  

   

• baseline Results
  

• We select three SOTA deep face recognition methods that have achieved top performance on major benchmark databases: LFW, IJB-A and MegaFace..

  COMPARISON OF VERIFICATION ACCURACY (%) ON LFW AND CPLFW USING FOUR SOTA DEEP FACE RECOGNITION MODELS.

  Method	LFW	CPLFW
  Centerface1	98.75%	77.48%
  SphereFace2	99.27%	81.40%
  VGGFace23	99.43%	84.00%
  ArcFace4	99.82%	92.08%
  HUMAN-Individual	97.27%	81.21%
  HUMAN-Fusion	99.85%	85.24%

  
  

  COMPARISON OF 10-FOLD VALIDATION ERROR (%) OF THREE SOTA DEEP FACE RECOGNITION MODELS. THE INCREASE OF ERROR IS ALSO ENUMERATED WHEN TRANSFERRING FROM LFW TO CPLFW.

  Method	LFW	CPLFW
  Centerface1	1.17	22.52 ( ↑ 1925%)
  SphereFace2	0.65	18.60 ( ↑ 2862%)
  VGGFace23	0.49	16.00 ( ↑ 3265%)

1. A discriminative feature learning approach for deep face recognition. In European Conference on Computer Vision, Springer, 2016, pp. 499–515.

2. Deep hyperspherical learning. In NIPS, 2017, pp. 3953–3963.

3. Q. Cao, L. Shen, W. Xie, O. M. Parkhi, and A. Zisserman. Vggface2: A dataset for recognising faces across pose and age. arXiv preprint arXiv：1710.08092, 2017.

4. Arcface: Additive angular margin loss for deep face recognition. arXiv preprint arXiv：1801.05599, 2018.

• Contact

• Please contact Tianyue Zheng (2231135739@qq.com) and Weihong Deng for questions about the database.