TU Darmstadt / ULB / TUbiblio

Mask-invariant Face Recognition through Template-level Knowledge Distillation

Huber, Marco ; Boutros, Fadi ; Kirchbuchner, Florian ; Damer, Naser (2021)
Mask-invariant Face Recognition through Template-level Knowledge Distillation.
16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021). virtual Conference (15.-18.12.2021)
doi: 10.1109/FG52635.2021.9667081
Konferenzveröffentlichung, Bibliographie

Kurzbeschreibung (Abstract)

The emergence of the global COVID-19 pandemic poses new challenges for biometrics. Not only are contactless biometric identification options becoming more important, but face recognition has also recently been confronted with the frequent wearing of masks. These masks affect the performance of previous face recognition systems, as they hide important identity information. In this paper, we propose a mask-invariant face recognition solution (MaskInv) that utilizes template-level knowledge distillation within a training paradigm that aims at producing embeddings of masked faces that are similar to those of non-masked faces of the same identities. In addition to the distilled knowledge, the student network benefits from additional guidance by margin-based identity classification loss, ElasticFace, using masked and non-masked faces. In a step-wise ablation study on two real masked face databases and five mainstream databases with synthetic masks, we prove the rationalization of our MaskInv approach. Our proposed solution outperforms previous state-of-the-art (SOTA) academic solutions in the recent MFRC-21 challenge in both scenarios, masked vs masked and masked vs non-masked, and also outperforms the previous solution on the MFR2 dataset. Furthermore, we demonstrate that the proposed model can still perform well on unmasked faces with only a minor loss in verification performance. The code, the trained models, as well as the evaluation protocol on the synthetically masked data are publicly available: https://github.com/fdbtrs/Masked-Face-Recognition-KD.

Typ des Eintrags: Konferenzveröffentlichung
Erschienen: 2021
Autor(en): Huber, Marco ; Boutros, Fadi ; Kirchbuchner, Florian ; Damer, Naser
Art des Eintrags: Bibliographie
Titel: Mask-invariant Face Recognition through Template-level Knowledge Distillation
Sprache: Englisch
Publikationsjahr: 2021
Verlag: IEEE
Buchtitel: Proceedings: 2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)
Veranstaltungstitel: 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)
Veranstaltungsort: virtual Conference
Veranstaltungsdatum: 15.-18.12.2021
DOI: 10.1109/FG52635.2021.9667081
Kurzbeschreibung (Abstract):

The emergence of the global COVID-19 pandemic poses new challenges for biometrics. Not only are contactless biometric identification options becoming more important, but face recognition has also recently been confronted with the frequent wearing of masks. These masks affect the performance of previous face recognition systems, as they hide important identity information. In this paper, we propose a mask-invariant face recognition solution (MaskInv) that utilizes template-level knowledge distillation within a training paradigm that aims at producing embeddings of masked faces that are similar to those of non-masked faces of the same identities. In addition to the distilled knowledge, the student network benefits from additional guidance by margin-based identity classification loss, ElasticFace, using masked and non-masked faces. In a step-wise ablation study on two real masked face databases and five mainstream databases with synthetic masks, we prove the rationalization of our MaskInv approach. Our proposed solution outperforms previous state-of-the-art (SOTA) academic solutions in the recent MFRC-21 challenge in both scenarios, masked vs masked and masked vs non-masked, and also outperforms the previous solution on the MFR2 dataset. Furthermore, we demonstrate that the proposed model can still perform well on unmasked faces with only a minor loss in verification performance. The code, the trained models, as well as the evaluation protocol on the synthetically masked data are publicly available: https://github.com/fdbtrs/Masked-Face-Recognition-KD.

Freie Schlagworte: Face recognition, Machine learning, Deep learning, Biometrics
Fachbereich(e)/-gebiet(e): 20 Fachbereich Informatik
20 Fachbereich Informatik > Graphisch-Interaktive Systeme
Hinterlegungsdatum: 03 Mär 2022 08:50
Letzte Änderung: 19 Okt 2023 06:18
PPN: 497528134
Export:
Suche nach Titel in: TUfind oder in Google
Frage zum Eintrag Frage zum Eintrag

Optionen (nur für Redakteure)
Redaktionelle Details anzeigen Redaktionelle Details anzeigen