Deep Heterogeneous Face Recognition Networks Based on Cross-Modal Distillation and an Equitable Distance Metric

Christopher Reale, Hyungtae Lee, Heesung Kwon

CVPRW 2017 pp. 226-232

doi:10.1109/CVPRW.2017.34 /cvprw/2017/reale2017cvprw-deep/

Abstract

In this work we present three methods to improve a deep convolutional neural network approach to near-infrared heterogeneous face recognition. We first present a method to distill extra information from a pre-trained visible face network through the output logits of the network. Next, we put forth an altered contrastive loss function that uses the ℓ1 norm instead of the ℓ2 norm as a distance metric. Finally, we propose to improve the initialization network by training it for more iterations. We present the results of experiments of these methods on two widely used near-infrared heterogeneous face recognition datasets and compare them to the state-of-the-art.

CVPRW Semantic Scholar

Cite

Text

Reale et al. "Deep Heterogeneous Face Recognition Networks Based on Cross-Modal Distillation and an Equitable Distance Metric." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017. doi:10.1109/CVPRW.2017.34

Markdown

[Reale et al. "Deep Heterogeneous Face Recognition Networks Based on Cross-Modal Distillation and an Equitable Distance Metric." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017.](https://mlanthology.org/cvprw/2017/reale2017cvprw-deep/) doi:10.1109/CVPRW.2017.34

BibTeX

@inproceedings{reale2017cvprw-deep,
  title     = {{Deep Heterogeneous Face Recognition Networks Based on Cross-Modal Distillation and an Equitable Distance Metric}},
  author    = {Reale, Christopher and Lee, Hyungtae and Kwon, Heesung},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2017},
  pages     = {226-232},
  doi       = {10.1109/CVPRW.2017.34},
  url       = {https://mlanthology.org/cvprw/2017/reale2017cvprw-deep/}
}