Improving Face Recognition with Large Age Gaps by Learning to Distinguish Children

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 42
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorLee, Jungsooko
dc.contributor.authorYun, Jooyeolko
dc.contributor.authorPark, Sunghyunko
dc.contributor.authorKim, Yonggyuko
dc.contributor.authorChoo, Jaegulko
dc.identifier.citationThe 32nd British Machine Vision Conference, BMVC 2021-
dc.description.abstractDespite the unprecedented improvement of face recognition, existing face recognition models still show considerably low performances in determining whether a pair of child and adult images belong to the same identity. Previous approaches mainly focused on increasing the similarity between child and adult images of a given identity to overcome the discrepancy of facial appearances due to aging. However, we observe that reducing the similarity between child images of different identities is crucial for learning distinct features among children and thus improving face recognition performance in child-adult pairs. Based on this intuition, we propose a novel loss function called the Inter-Prototype loss which minimizes the similarity between child images. Unlike the previous studies, the Inter-Prototype loss does not require additional child images or training additional learnable parameters. Our extensive experiments and in-depth analyses show that our approach outperforms existing baselines in face recognition with child adult pairs. Our code and newly-constructed test sets of child-adult pairs are available at this link 1.-
dc.publisherBritish Machine Vision Association-
dc.titleImproving Face Recognition with Large Age Gaps by Learning to Distinguish Children-
dc.citation.publicationnameThe 32nd British Machine Vision Conference, BMVC 2021-
dc.contributor.localauthorChoo, Jaegul-
dc.contributor.nonIdAuthorLee, Jungsoo-
dc.contributor.nonIdAuthorYun, Jooyeol-
dc.contributor.nonIdAuthorPark, Sunghyun-
dc.contributor.nonIdAuthorKim, Yonggyu-
Appears in Collection
RIMS Conference Papers
Files in This Item
There are no files associated with this item.


  • mendeley


rss_1.0 rss_2.0 atom_1.0