Exploring Disentangled Feature Representation Beyond Face Identification

  title={Exploring Disentangled Feature Representation Beyond Face Identification},
  author={Y. Liu and Fangyin Wei and J. Shao and Lu Sheng and J. Yan and X. Wang},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  • Y. Liu, Fangyin Wei, +3 authors X. Wang
  • Published 2018
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • This paper proposes learning disentangled but complementary face features with a minimal supervision by face identification. [...] Key Method Thanks to the design of two-stream cues, the learned disentangled features represent not only the identity or attribute but the complete input image. Comprehensive evaluations further demonstrate that the proposed features not only preserve state-of-the-art identity verification performance on LFW, but also acquire comparable discriminative power for face attribute…Expand Abstract

    Figures, Tables, and Topics from this paper.

    Style Aggregated Network for Facial Landmark Detection
    • 130
    • PDF
    Talking Face Generation by Adversarially Disentangled Audio-Visual Representation
    • 61
    • PDF
    Unsupervised Domain-Specific Deblurring via Disentangled Representations
    • 31
    • PDF
    Decorrelated Adversarial Learning for Age-Invariant Face Recognition
    • 15
    • PDF
    DebFace: De-biasing Face Recognition
    • 12
    • PDF
    Deep Face Recognition: A Survey
    • 21
    • PDF


    Publications referenced by this paper.
    Generative Adversarial Nets
    • 17,785
    • Highly Influential
    • PDF
    FaceNet: A unified embedding for face recognition and clustering
    • 5,208
    • PDF
    DeepFace: Closing the Gap to Human-Level Performance in Face Verification
    • 3,995
    • PDF
    Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
    • 18,887
    • PDF
    Deep Learning Face Attributes in the Wild
    • 2,678
    • PDF
    Image-to-Image Translation with Conditional Adversarial Networks
    • 6,274
    • PDF
    Representation Learning: A Review and New Perspectives
    • 6,247
    • PDF
    Deep Learning Face Representation by Joint Identification-Verification
    • 1,508
    • PDF
    Extracting and composing robust features with denoising autoencoders
    • 4,021
    • PDF
    Auto-Encoding Variational Bayes
    • 9,149
    • PDF