FARE: A Deep Learning-Based Framework for Radar-based Face Recognition and Out-of-distribution Detection

TL;DR

This paper introduces FARE, a deep learning framework that uses radar data for accurate face recognition and effective out-of-distribution detection, with high accuracy and AUROC on a custom dataset.

Contribution

The work presents a novel radar-based face recognition system with a dual-path architecture for ID classification and OOD detection, trained in two stages.

Findings

ID classification accuracy of 99.30%

OOD detection AUROC of 96.91%

Effective use of FMCW radar data for face recognition

Abstract

In this work, we propose a novel pipeline for face recognition and out-of-distribution (OOD) detection using short-range FMCW radar. The proposed system utilizes Range-Doppler and micro Range-Doppler Images. The architecture features a primary path (PP) responsible for the classification of in-distribution (ID) faces, complemented by intermediate paths (IPs) dedicated to OOD detection. The network is trained in two stages: first, the PP is trained using triplet loss to optimize ID face classification. In the second stage, the PP is frozen, and the IPs-comprising simple linear autoencoder networks-are trained specifically for OOD detection. Using our dataset generated with a 60 GHz FMCW radar, our method achieves an ID classification accuracy of 99.30% and an OOD detection AUROC of 96.91%.