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

TL;DR

This paper introduces OREO, an occlusion-aware face recognition method that enhances robustness to occlusions by using local attention and a balanced training strategy, significantly improving accuracy in occluded scenarios.

Contribution

The paper proposes a novel occlusion-aware face recognition approach with an attention mechanism and a balanced training strategy, improving robustness against occlusions.

Findings

OREO improves occlusion robustness by 10.17% in single-image scenarios.

OREO outperforms baseline by approximately 2% in rank-1 accuracy.

Extensive experiments validate the effectiveness of the proposed method.

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.