Proxy embeddings for face identification among multi-pose templates

Weronika Gutfeter , Andrzej Pacut

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.

Author Weronika Gutfeter - Scientific and Academic Computer Network (NASK PIB) [Naukowej i Akademickiej Sieci Komputerowej, Warszawa]
Weronika Gutfeter,,
-
-
, Andrzej Pacut (FEIT / AK) - Scientific and Academic Computer Network (NASK PIB) [Scientific and Academic Computer Network (NASK PIB)]
Andrzej Pacut,,
- The Institute of Control and Computation Engineering
- Naukowa i Akademicka Sieć Komputerowa
Journal seriesVISIGRAPP 2020 - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Issue year2020
Vol5
Pages513-520
DOIDOI:10.5220/0009166505130520
URL https://www.scitepress.org/AffiliationsProfile.aspx?Org=lC6vJN4uLHAgLaer6InoDl1V8iJEwzPsLBnmq19SyFuq55rQYciYsY1i2bLoFp3xQemlUgG/mhAU+uv4q+hOCQ==&t=1
Languageen angielski
Score (nominal)5
Score sourcejournalList
ScoreMinisterial score = 5.0, 28-08-2020, ArticleFromJournal
Publication indicators Scopus Citations = 0
Citation count*
Cite
Share Share

Get link to the record


* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.
Back
Confirmation
Are you sure?