TY - GEN
T1 - On improving the generalization of face recognition in the presence of occlusions
AU - Xu, Xiang
AU - Sarafianos, Nikolaos
AU - Kakadiaris, Ioannis A.
N1 - Funding Information:
Acknowledgment This material was supported by the U.S. Department of Homeland Security under Grant Award Number 2017-STBTI-0001-0201 with resources provided by the Core facility for Advanced Computing and Data Science at the University of Houston.
Publisher Copyright:
© 2020 IEEE.
PY - 2020/6
Y1 - 2020/6
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85090141126&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85090141126&partnerID=8YFLogxK
U2 - 10.1109/CVPRW50498.2020.00407
DO - 10.1109/CVPRW50498.2020.00407
M3 - Conference contribution
AN - SCOPUS:85090141126
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 3470
EP - 3480
BT - Proceedings - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020
Y2 - 14 June 2020 through 19 June 2020
ER -