MoDE: Mixture of Diffusion Experts for Any Occluded Face Recognition

TL;DR

This paper introduces MoDE, a mixture of diffusion experts with identity gating, to improve occluded face recognition by generating multiple reconstructions and adaptively integrating them, significantly enhancing performance on occlusion challenges.

Contribution

The paper proposes a novel plug-and-play MoDE framework that leverages multiple diffusion-based experts and identity gating to effectively recognize occluded faces.

Findings

Outperforms existing methods on public face datasets.

Effectively handles various types and severities of occlusion.

Demonstrates robustness in real-world occlusion scenarios.

Abstract

With the continuous impact of epidemics, people have become accustomed to wearing masks. However, most current occluded face recognition (OFR) algorithms lack prior knowledge of occlusions, resulting in poor performance when dealing with occluded faces of varying types and severity in reality. Recognizing occluded faces is still a significant challenge, which greatly affects the convenience of people's daily lives. In this paper, we propose an identity-gated mixture of diffusion experts (MoDE) for OFR. Each diffusion-based generative expert estimates one possible complete image for occluded faces. Considering the random sampling process of the diffusion model, which introduces inevitable differences and variations between the inpainted faces and the real ones. To ensemble effective information from multi-reconstructed faces, we introduce an identity-gating network to evaluate the contribution of each reconstructed face to the identity and adaptively integrate the predictions in the decision space. Moreover, our MoDE is a plug-and-play module for most existing face recognition models. Extensive experiments on three public face datasets and two datasets in the wild validate our advanced performance for various occlusions in comparison with the competing methods.