On Improving the Generalization of Face Recognition in the Presence of Occlusions

Abstract

In this paper, we address a key limitation of existing 2D face recognition methods: robustness to occlusions. To accomplish this task, we systematically analyzed the impact of facial attributes on the performance of a state-of-the-art face recognition method and through extensive experimentation, quantitatively analyzed the performance degradation under different types of occlusion. Our proposed Occlusion-aware face REcOgnition (OREO) approach learned discriminative facial templates despite the presence of such occlusions. First, an attention mechanism was proposed that extracted local identity-related region. The local features were then aggregated with the global representations to form a single template. Second, a simple, yet effective, training strategy was introduced to balance the non-occluded and occluded facial images. Extensive experiments demonstrated that OREO improved the generalization ability of face recognition under occlusions by (10.17%) in a single-image-based setting and outperformed the baseline by approximately (2%) in terms of rank-1 accuracy in an image-set-based scenario.

arXiv commentTechnical Report

References in corpus (14)

• SphereFace: Deep Hypersphere Embedding for Face Recognition
• Face Attention Network: An Effective Face Detector for the Occluded Faces
• Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis
• Learn To Pay Attention
• Multi-Context Attention for Human Pose Estimation
• Multicolumn Networks for Face Recognition
• Towards End-to-End Face Recognition through Alignment Learning
• Neural Aggregation Network for Video Face Recognition
• Occlusion Robust Face Recognition Based on Mask Learning with PairwiseDifferential Siamese Network
• Towards Large-Pose Face Frontalization in the Wild
• Towards Open-Set Identity Preserving Face Synthesis
• Pose-Robust Face Recognition via Deep Residual Equivariant Mapping
• Orthogonal Deep Features Decomposition for Age-Invariant Face Recognition
• Face Synthesis for Eyeglass-Robust Face Recognition