Proxy Embeddings for Face Identification among Multi-Pose Templates

Weronika Gutfeter, Andrzej Pacut

2020

Abstract

Many of a large scale face identification systems operates on databases containing images showing heads in multiple poses (from frontal to full profiles). However, as it was shown in the paper, off-the-shelf methods are not able to take advantage of this particular data structure. The main idea behind our work was to adapt the methods proposed for multi-view and semi-3D objects classification to the multi-pose face recognition problem. The proposed approach involves neural network training with proxy embeddings and building the gallery templates out of aggregated samples. A benchmark testing scenario is proposed for the purpose of the problem, which is based on the linked gallery and probes databases. The gallery database consists of multi-pose face images taken under controlled conditions, and the probes database contains samples of in-the-wild type. Both databases must be linked, having at least partially common labels. Two variants of the proposed training procedures were tested, namely, the neighbourhood component analysis with proxies (NCA-proxies) and the triplet margin loss with proxies (triplet-proxies). It is shown that the proposed methods perform better than models trained with cross-entropy loss and than off-the-shelf methods. Rank-1 accuracy was improved from 48.82% for off-the-shelf baseline to 86.86% for NCA-proxies. In addition, transfer of proxy points between two independently trained models was discussed, similarly to hyper-parameters transfer methodology. Proxy embeddings transfer opens a possibility of training two domain-specific networks with respect to two datasets identification schema.

Paper Citation

in Harvard Style

Gutfeter W. and Pacut A. (2020). Proxy Embeddings for Face Identification among Multi-Pose Templates. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP; ISBN 978-989-758-402-2, SciTePress, pages 513-520. DOI: 10.5220/0009166505130520

in Bibtex Style

@conference{visapp20,
author={Weronika Gutfeter and Andrzej Pacut},
title={Proxy Embeddings for Face Identification among Multi-Pose Templates},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP},
year={2020},
pages={513-520},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009166505130520},
isbn={978-989-758-402-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP
TI - Proxy Embeddings for Face Identification among Multi-Pose Templates
SN - 978-989-758-402-2
AU - Gutfeter W.
AU - Pacut A.
PY - 2020
SP - 513
EP - 520
DO - 10.5220/0009166505130520
PB - SciTePress