English

Age Prediction From Face Images Via Contrastive Learning

Computer Vision and Pattern Recognition 2023-08-24 v1

Abstract

This paper presents a novel approach for accurately estimating age from face images, which overcomes the challenge of collecting a large dataset of individuals with the same identity at different ages. Instead, we leverage readily available face datasets of different people at different ages and aim to extract age-related features using contrastive learning. Our method emphasizes these relevant features while suppressing identity-related features using a combination of cosine similarity and triplet margin losses. We demonstrate the effectiveness of our proposed approach by achieving state-of-the-art performance on two public datasets, FG-NET and MORPH-II.

Keywords

Cite

@article{arxiv.2308.11896,
  title  = {Age Prediction From Face Images Via Contrastive Learning},
  author = {Yeongnam Chae and Poulami Raha and Mijung Kim and Bjorn Stenger},
  journal= {arXiv preprint arXiv:2308.11896},
  year   = {2023}
}

Comments

MVA2023

R2 v1 2026-06-28T12:02:09.392Z