Age Prediction From Face Images Via Contrastive Learning
This addresses the challenge of limited same-identity age data for computer vision applications, though it is incremental in improving accuracy.
The paper tackles the problem of age estimation from face images by using contrastive learning to extract age-related features from datasets of different people at different ages, achieving state-of-the-art performance on FG-NET and MORPH-II datasets.
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.