Learning Deep Convolutional Embeddings for Face Representation Using Joint Sample- and Set-Based Supervision

Abstract

In this work, we investigate several methods and strategies to learn deep embeddings for face recognition, using joint sample- and set-based optimization. We explain our framework that expands traditional learning with set-based supervision together with the strategies used to maintain set characteristics. We, then, briefly review the related set-based loss functions, and subsequently we propose a novel Max-Margin Loss which maximizes maximum possible inter-class margin with assistance of Support Vector Machines (SVMs). It implicitly pushes all the samples towards correct side of the margin with a vector perpendicular to the hyperplane and a strength inversely proportional to the distance to it. We show that the introduced loss outperform the previous sample-based and set-based ones in terms verification of faces on two commonly used benchmarks.

Cite

Text

Gecer et al. "Learning Deep Convolutional Embeddings for Face Representation Using Joint Sample- and Set-Based Supervision." IEEE/CVF International Conference on Computer Vision Workshops, 2017. doi:10.1109/ICCVW.2017.195

Markdown

[Gecer et al. "Learning Deep Convolutional Embeddings for Face Representation Using Joint Sample- and Set-Based Supervision." IEEE/CVF International Conference on Computer Vision Workshops, 2017.](https://mlanthology.org/iccvw/2017/gecer2017iccvw-learning/) doi:10.1109/ICCVW.2017.195

BibTeX

@inproceedings{gecer2017iccvw-learning,
  title     = {{Learning Deep Convolutional Embeddings for Face Representation Using Joint Sample- and Set-Based Supervision}},
  author    = {Gecer, Baris and Balntas, Vassileios and Kim, Tae-Kyun},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2017},
  pages     = {1665-1672},
  doi       = {10.1109/ICCVW.2017.195},
  url       = {https://mlanthology.org/iccvw/2017/gecer2017iccvw-learning/}
}