MeFEm: Medical Face Embedding model

TL;DR

MeFEm is a novel vision model for biometric and medical facial analysis that employs innovative masking and loss strategies, outperforming existing models on key tasks with less data.

Contribution

Introduces MeFEm, a new facial embedding model with unique modifications like axial stripe masking and probabilistic CLS reassignment, achieving superior performance.

Findings

Outperforms FaRL and Franca on anthropometric tasks

Effective BMI estimation on a new consolidated dataset

Uses less data than comparable models

Abstract

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.