A Progressive Learning Framework for Unconstrained Face Recognition

The carefully designed backbone network, the increase of training data and the improved training skills have boosted the performance of modern face recognition systems. However, in some deployment cases which aim at model compactness and energy efficiency, some of the existing systems may fail due to the high complexity. Lightweight Face Recognition Challenge is proposed in order to make some progress in this direction and establishes a new comprehensive benchmark. In this challenge, we have designed a light weight backbone architecture and all the parameters are trained in a progressive way. Finally we achieve the 5th in track 1 and the 4th in track 3.

[1]  Mark Sandler,et al.  MobileNetV2: Inverted Residuals and Linear Bottlenecks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[2]  Shifeng Zhang,et al.  Support Vector Guided Softmax Loss for Face Recognition , 2018, ArXiv.

[3]  Yang Liu,et al.  MobileFaceNets: Efficient CNNs for Accurate Real-time Face Verification on Mobile Devices , 2018, CCBR.

[4]  Stefanos Zafeiriou,et al.  ArcFace: Additive Angular Margin Loss for Deep Face Recognition , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Kha Gia Quach,et al.  MobiFace: A Lightweight Deep Learning Face Recognition on Mobile Devices , 2019, 2019 IEEE 10th International Conference on Biometrics Theory, Applications and Systems (BTAS).

[6]  Kai Zhao,et al.  RegularFace: Deep Face Recognition via Exclusive Regularization , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Xiangyu Zhang,et al.  ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design , 2018, ECCV.

[8]  Lucas Beyer,et al.  In Defense of the Triplet Loss for Person Re-Identification , 2017, ArXiv.

[9]  Jiwen Lu,et al.  UniformFace: Learning Deep Equidistributed Representation for Face Recognition , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Dong Liu,et al.  IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural Networks , 2018, BMVC.

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

[12]  Quoc V. Le,et al.  Searching for MobileNetV3 , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[13]  Stefanos Zafeiriou,et al.  AgeDB: The First Manually Collected, In-the-Wild Age Database , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[14]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[15]  Xiangyu Zhang,et al.  ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[16]  Forrest N. Iandola,et al.  SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size , 2016, ArXiv.

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

[18]  Jean-Christophe Filliâtre,et al.  A persistent union-find data structure , 2007, ML '07.

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

[20]  Jian Cheng,et al.  Additive Margin Softmax for Face Verification , 2018, IEEE Signal Processing Letters.

[21]  Jingdong Wang,et al.  Interleaved Group Convolutions , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[22]  Stefanos Zafeiriou,et al.  RetinaFace: Single-stage Dense Face Localisation in the Wild , 2019, ArXiv.

[23]  Gang Sun,et al.  Squeeze-and-Excitation Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[24]  Xing Ji,et al.  CosFace: Large Margin Cosine Loss for Deep Face Recognition , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[25]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[26]  Ira Kemelmacher-Shlizerman,et al.  MegaFace: A Million Faces for Recognition at Scale , 2015, ArXiv.

[27]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

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

[29]  Tieniu Tan,et al.  A Light CNN for Deep Face Representation With Noisy Labels , 2015, IEEE Transactions on Information Forensics and Security.

[30]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

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

[32]  Kurt Keutzer,et al.  SqueezeNext: Hardware-Aware Neural Network Design , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[33]  Carlos D. Castillo,et al.  Frontal to profile face verification in the wild , 2016, 2016 IEEE Winter Conference on Applications of Computer Vision (WACV).

[34]  Nikos Komodakis,et al.  Wide Residual Networks , 2016, BMVC.

[35]  Debing Zhang,et al.  Lightweight Face Recognition Challenge , 2019, 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW).

[36]  Jianhuang Lai,et al.  Interleaved Structured Sparse Convolutional Neural Networks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[37]  Meng Yang,et al.  Large-Margin Softmax Loss for Convolutional Neural Networks , 2016, ICML.