Enhancing Low-resolution Face Recognition with Feature Similarity Knowledge Distillation

In this study, we introduce a feature knowledge distillation framework to improve low-resolution (LR) face recognition performance using knowledge obtained from high-resolution (HR) images. The proposed framework transfers informative features from an HR-trained network to an LR-trained network by reducing the distance between them. A cosine similarity measure was employed as a distance metric to effectively align the HR and LR features. This approach differs from conventional knowledge distillation frameworks, which use the L_p distance metrics and offer the advantage of converging well when reducing the distance between features of different resolutions. Our framework achieved a 3% improvement over the previous state-of-the-art method on the AgeDB-30 benchmark without bells and whistles, while maintaining a strong performance on HR images. The effectiveness of cosine similarity as a distance metric was validated through statistical analysis, making our approach a promising solution for real-world applications in which LR images are frequently encountered. The code and pretrained models are publicly available on https://github.com/gist-ailab/feature-similarity-KD.

[1]  Sungho Shin,et al.  Teaching Where to Look: Attention Similarity Knowledge Distillation for Low Resolution Face Recognition , 2022, ECCV.

[2]  Anil K. Jain,et al.  AdaFace: Quality Adaptive Margin for Face Recognition , 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Xiaolin Hu,et al.  DAM: Discrepancy Alignment Metric for Face Recognition , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[4]  Bryan Hooi,et al.  Spherical Confidence Learning for Face Recognition , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Stefanos Zafeiriou,et al.  Variational Prototype Learning for Deep Face Recognition , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Jae-Joon Han,et al.  Quality-Agnostic Image Recognition via Invertible Decoder , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Rama Chellappa,et al.  S2LD: Semi-Supervised Landmark Detection in Low Resolution Images and Impact on Face Verification , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[8]  Feiyue Huang,et al.  CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Yichen Wei,et al.  Data Uncertainty Learning in Face Recognition , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  F. V. Massoli,et al.  Cross-Resolution Learning for Face Recognition , 2019, Image Vis. Comput..

[11]  Neil D. Lawrence,et al.  Variational Information Distillation for Knowledge Transfer , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Yan Lu,et al.  Relational Knowledge Distillation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  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).

[14]  Shaogang Gong,et al.  Low-Resolution Face Recognition , 2018, ACCV.

[15]  Arnold W. M. Smeulders,et al.  i-RevNet: Deep Invertible Networks , 2018, ICLR.

[16]  Anil K. Jain,et al.  IARPA Janus Benchmark - C: Face Dataset and Protocol , 2018, 2018 International Conference on Biometrics (ICB).

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

[18]  Junmo Kim,et al.  A Gift from Knowledge Distillation: Fast Optimization, Network Minimization and Transfer Learning , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  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).

[20]  Anil K. Jain,et al.  IARPA Janus Benchmark-B Face Dataset , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[21]  Xiaoming Liu,et al.  Disentangled Representation Learning GAN for Pose-Invariant Face Recognition , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[23]  Nikos Komodakis,et al.  Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer , 2016, ICLR.

[24]  Yu Qiao,et al.  Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks , 2016, IEEE Signal Processing Letters.

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

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

[27]  Ira Kemelmacher-Shlizerman,et al.  The MegaFace Benchmark: 1 Million Faces for Recognition at Scale , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Yoshua Bengio,et al.  FitNets: Hints for Thin Deep Nets , 2014, ICLR.

[29]  Xiaogang Wang,et al.  Deep Learning Face Attributes in the Wild , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

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

[31]  Andrew Y. Ng,et al.  Reading Digits in Natural Images with Unsupervised Feature Learning , 2011 .

[32]  Student,et al.  THE PROBABLE ERROR OF A MEAN , 1908 .

[33]  K. Pearson Mathematical Contributions to the Theory of Evolution. III. Regression, Heredity, and Panmixia , 1896 .