FaceNet: A Unified Embedding for Face Recognition and Clustering. Despite significant recent advances in the field of face recognition, implementing face verification and recognition efficiently at scale presents serious challenges to current approaches. In this paper we present a system, called FaceNet, that directly learns a mapping from face images to a compact Euclidean space where distances directly correspond to a measure of face similarity. Once this space has been produced, tasks such as face recognition, verification and clustering can be easily implemented using standard techniques with FaceNet embeddings as feature vectors. Our method uses a deep convolutional network trained to directly optimize the embedding itself, rather than an intermediate bottleneck layer as in previous deep learning approaches. To train, we use triplets of roughly aligned matching / non-matching face patches generated using a novel online triplet mining method. The benefit of our approach is much greater representational efficiency: we achieve state-of-the-art face recognition performance using only 128-bytes per face. On the widely used Labeled Faces in the Wild (LFW) dataset, our system achieves a new record accuracy of 99.63%. On YouTube Faces DB it achieves 95.12%. Our system cuts the error rate in comparison to the best published result by 30% on both datasets. We also introduce the concept of harmonic embeddings, and a harmonic triplet loss, which describe different versions of face embeddings (produced by different networks) that are compatible to each other and allow for direct comparison between each other.

References in zbMATH (referenced in 33 articles )

Showing results 1 to 20 of 33.
Sorted by year (citations)

1 2 next

  1. Serna, Ignacio; Morales, Aythami; Fierrez, Julian; Obradovich, Nick: Sensitive loss: improving accuracy and fairness of face representations with discrimination-aware deep learning (2022)
  2. Chen, Ling; Chen, Donghui; Yang, Fan; Sun, Jianling: A deep multi-task representation learning method for time series classification and retrieval (2021)
  3. Hussain, Khaled F.; Bassyouni, Mohamed Yousef; Gelenbe, Erol: Accurate, energy-efficient classification with spiking random neural network (2021)
  4. Jun Wang, Yinglu Liu, Yibo Hu, Hailin Shi, Tao Mei: FaceX-Zoo: A PyTorch Toolbox for Face Recognition (2021) arXiv
  5. Ma, Guixiang; Ahmed, Nesreen K.; Willke, Theodore L.; Yu, Philip S.: Deep graph similarity learning: a survey (2021)
  6. Pacchiardi, Lorenzo; Künzli, Pierre; Chopard, Bastien; Schöngens, Marcel; Dutta, Ritabrata: Distance-learning for approximate Bayesian computation to model a volcanic eruption (2021)
  7. Qingzhong Wang, Pengfei Zhang, Haoyi Xiong, Jian Zhao: Face.evoLVe: A High-Performance Face Recognition Library (2021) arXiv
  8. Shimada, Takuya; Bao, Han; Sato, Issei; Sugiyama, Masashi: Classification from pairwise similarities/dissimilarities and unlabeled data via empirical risk minimization (2021)
  9. Taylor Arnold; Lauren Tilton: Distant Viewing Toolkit: A Python Package for the Analysis of Visual Culture (2021) not zbMATH
  10. Zhang, Hongjing; Zhan, Tianyang; Basu, Sugato; Davidson, Ian: A framework for deep constrained clustering (2021)
  11. Zhang, Xue; Wang, Changzhong; Fan, Xiaodong: Convex hull-based distance metric learning for image classification (2021)
  12. Amosov, O. S.; Amosova, S. G.; Zhiganov, S. V.; Ivanov, Yu. S.; Pashchenko, F. F.: Computational method for recognizing situations and objects in the frames of a continuous video stream using deep neural networks for access control systems (2020)
  13. Cui, Zhenghang; Charoenphakdee, Nontawat; Sato, Issei; Sugiyama, Masashi: Classification from triplet comparison data (2020)
  14. Duan, Jia; Zhou, Jiantao; Li, Yuanman: Privacy-preserving distributed deep learning based on secret sharing (2020)
  15. Qin, Zixuan; Yin, Mengxiao; Li, Guiqing; Yang, Feng: SP-Flow: self-supervised optical flow correspondence point prediction for real-time SLAM (2020)
  16. Valaitis, Vytautas; Marcinkevicius, Virginijus; Jurevicius, Rokas: Learning aerial image similarity using triplet networks (2020)
  17. Weinshall, Daphna; Amir, Dan: Theory of curriculum learning, with convex loss functions (2020)
  18. Xu, Yichong; Balakrishnan, Sivaraman; Singh, Aarti; Dubrawski, Artur: Regression with comparisons: escaping the curse of dimensionality with ordinal information (2020)
  19. Deng, Zhongying; Peng, Xiaojiang; Li, Zhifeng; Qiao, Yu: Mutual component convolutional neural networks for heterogeneous face recognition (2019)
  20. Görgel, Pelin; Simsek, Ahmet: Face recognition via deep stacked denoising sparse autoencoders (DSDSA) (2019)

1 2 next