Supervised Contrastive Learning for Snapshot Spectral Imaging Face Anti-Spoofing

TL;DR

This paper introduces a novel contrastive learning strategy that significantly improves face anti-spoofing accuracy using hyperspectral imaging, achieving zero error on a challenging dataset and winning a major challenge.

Contribution

It presents a re-balanced contrastive learning approach with data resampling and reweighting, specifically designed for hyperspectral face anti-spoofing, outperforming existing methods.

Findings

Achieved 0.0000% ACER on HySpeFAS dataset

Ranked first at CVPR 2024 Chalearn challenge

Effectively mitigated dataset imbalance and bias

Abstract

This study reveals a cutting-edge re-balanced contrastive learning strategy aimed at strengthening face anti-spoofing capabilities within facial recognition systems, with a focus on countering the challenges posed by printed photos, and highly realistic silicone or latex masks. Leveraging the HySpeFAS dataset, which benefits from Snapshot Spectral Imaging technology to provide hyperspectral images, our approach harmonizes class-level contrastive learning with data resampling and an innovative real-face oriented reweighting technique. This method effectively mitigates dataset imbalances and reduces identity-related biases. Notably, our strategy achieved an unprecedented 0.0000\% Average Classification Error Rate (ACER) on the HySpeFAS dataset, ranking first at the Chalearn Snapshot Spectral Imaging Face Anti-spoofing Challenge on CVPR 2024.