Metraipolis › archive › dc_971470a8dfbe

Faces or Models? Where the Age Gap in Facial Expression Recognition Comes From — arXiv:2611.00045

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00045
License (as archived)
CC0-1.0
Archived
2026-11-03T11:39:48.501Z
SHA-256 of the archived text
39c4283362317717004a397318689574b7ce09882d95aece1b9deca3b7210fba
Stable URL of this page
https://metraipolis.com/documento/dc_971470a8dfbe

How to cite

Faces or Models? Where the Age Gap in Facial Expression Recognition Comes From — arXiv:2611.00045 — arXiv (en), https://arxiv.org/abs/2611.00045 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_971470a8dfbe (Metraipolis archive dc_971470a8dfbe, sha256 39c4283362317717004a397318689574b7ce09882d95aece1b9deca3b7210fba)
BibTeX
@misc{dc971470a8dfbe,
  title = {Faces or Models? Where the Age Gap in Facial Expression Recognition Comes From — arXiv:2611.00045},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00045},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_971470a8dfbe; sha256 39c4283362317717004a397318689574b7ce09882d95aece1b9deca3b7210fba},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00045. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Facial expression recognition (FER) systems are increasingly used in elder care, yet their accuracy on older faces is rarely measured. This study evaluated five open-source FER models on the FACES database, which holds 2,052 posed photographs of 171 adults aged 19 to 80. The models cross three architectures (ResNet-18, POSTER++ and QCS) with two training datasets (RAF-DB and AffectNet). All models lost accuracy on older faces by 11.7 to 15.2 percentage points. Older faces were harder for people too: human raters lost 8.6 points, a classifier using only facial geometry lost 8.3, and for anger, fear, and happiness older adults differed more from one another when posing. On specific expressions the models fell much further than people did. AffectNet-trained models misread older neutral faces as sad or angry 62% of the time. RAF-DB-trained models lost fear, disgust, and anger instead. The gap persisted after controlling for architecture, image quality, cropping, and expression intensity. When only the final classification layer was refitted on older faces, the gap shrank from 11 to 21 points to 4 points or less, suggesting that the models' learned features can represent older faces and that the deficit lies in how the final layer was trained.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.00045 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T11:06:37.364Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).