Attention-based Partial Face Recognition

TL;DR

This paper introduces an attention-based method for recognizing partial faces in unconstrained environments, effectively handling occlusions by focusing on relevant facial regions and outperforming existing baselines.

Contribution

The paper presents a novel partial face recognition approach combining attentional pooling with a dedicated aggregation module, adapted loss functions, and comprehensive evaluation.

Findings

Outperforms all baseline methods on multiple benchmarks

Effectively handles naturally and synthetically occluded faces

Demonstrates the importance of diverse attention maps

Abstract

Photos of faces captured in unconstrained environments, such as large crowds, still constitute challenges for current face recognition approaches as often faces are occluded by objects or people in the foreground. However, few studies have addressed the task of recognizing partial faces. In this paper, we propose a novel approach to partial face recognition capable of recognizing faces with different occluded areas. We achieve this by combining attentional pooling of a ResNet's intermediate feature maps with a separate aggregation module. We further adapt common losses to partial faces in order to ensure that the attention maps are diverse and handle occluded parts. Our thorough analysis demonstrates that we outperform all baselines under multiple benchmark protocols, including naturally and synthetically occluded partial faces. This suggests that our method successfully focuses on the relevant parts of the occluded face.