Deep face recognition with weighted center loss

ID face photos are widely used for identity verification in many real-world applications. In these cases, the face from ID photo is expected to compare with the face obtained from the daily life image. To improve the ID/life face verification performance, the datasets containing various ID face photos and daily life face images are always needed to train an available CNN model for feature extraction. However, it’s really hard to get uniform distributed data for both the ID photos and daily life images. In most face datasets, each subject only contains one ID photo (for example, obtained from the identity card) while contains varies of life images. This imbalanced distribution causes the difficulty of learning a general deep feature representation for both the ID and life faces, since the daily life images tend to have a higher impact on the feature learning than the ID photos. To address this challenge, we propose a weighted center loss which aims to learn a center of deep features for each class and penalizes the distance between the image features and their corresponding class centers with different weights. By emphasizing the ID photo features in the loss computation, our weighted center loss can train a general CNN which obviously narrows the distance between the ID and life faces. Final experiments demonstrate that with the joint supervision of softmax and weighted center loss, our proposed framework can minimize the intra-class variations caused by the imbalanced ID/life data distribution and significantly improve the ID face based verification accuracy.

[1]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Xiaoou Tang,et al.  Image Super-Resolution Using Deep Convolutional Networks , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Jing Liu,et al.  Objectness-aware Semantic Segmentation , 2016, ACM Multimedia.

[4]  Shengcai Liao,et al.  Learning Face Representation from Scratch , 2014, ArXiv.

[5]  Jian Yang,et al.  Sparse Deep Stacking Network for Image Classification , 2015, AAAI.

[6]  Ravi Kiran Sarvadevabhatla,et al.  SwiDeN: Convolutional Neural Networks For Depiction Invariant Object Recognition , 2016, ACM Multimedia.

[7]  Jian Yang,et al.  Image Super-Resolution via Deep Recursive Residual Network , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Marwan Mattar,et al.  Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments , 2008 .

[9]  Yuxiao Hu,et al.  MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition , 2016, ECCV.

[10]  Qi Yin,et al.  Naive-Deep Face Recognition: Touching the Limit of LFW Benchmark or Not? , 2015, ArXiv.

[11]  Tal Hassner,et al.  Face recognition in unconstrained videos with matched background similarity , 2011, CVPR 2011.

[12]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[13]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[14]  Jun Li,et al.  Deep Face Recognition with Center Invariant Loss , 2017, ACM Multimedia.

[15]  Xiaogang Wang,et al.  Deep Learning Face Representation by Joint Identification-Verification , 2014, NIPS.

[16]  Bhiksha Raj,et al.  SphereFace: Deep Hypersphere Embedding for Face Recognition , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Xiaogang Wang,et al.  DeepID3: Face Recognition with Very Deep Neural Networks , 2015, ArXiv.

[18]  Rob Fergus,et al.  Depth Map Prediction from a Single Image using a Multi-Scale Deep Network , 2014, NIPS.

[19]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Yu Qiao,et al.  A Discriminative Feature Learning Approach for Deep Face Recognition , 2016, ECCV.