MeFEm: Medical Face Embedding model
This provides a domain-specific tool for biometric and medical analysis from facial images, addressing domain bias in existing data.
The authors tackled medical analysis from facial images by developing MeFEm, a vision model based on a modified JEPA architecture, which outperformed strong baselines like FaRL and Franca on core anthropometric tasks using significantly less data and showed promising results on BMI estimation.
We present MeFEm, a vision model based on a modified Joint Embedding Predictive Architecture (JEPA) for biometric and medical analysis from facial images. Key modifications include an axial stripe masking strategy to focus learning on semantically relevant regions, a circular loss weighting scheme, and the probabilistic reassignment of the CLS token for high quality linear probing. Trained on a consolidated dataset of curated images, MeFEm outperforms strong baselines like FaRL and Franca on core anthropometric tasks despite using significantly less data. It also shows promising results on Body Mass Index (BMI) estimation, evaluated on a novel, consolidated closed-source dataset that addresses the domain bias prevalent in existing data. Model weights are available at https://huggingface.co/boretsyury/MeFEm , offering a strong baseline for future work in this domain.