Decision-Threshold Transferability and Robustness in Masked Face Verification

Masked-face verification systems apply decision thresholds set on development data, but whether these keep their target false acceptance rate (FAR) after deployment is rarely tested. We transferred thresholds set at 0.1% and 1% FAR on synthetically masked LFW to two external masked-face datasets, RMFDVER and the mixed-provenance COMASK20, using two ArcFace/MS1M-pretrained models and identity-level bootstrapping. At the 1% target, the observed FAR rose to 2.5–2.8% on RMFDVER and 16–21% on COMASK20. FAR inflation also occurred for reconstructed unmasked comparisons, and transfer between the external datasets was either too permissive or too strict. Model replacement and synthetic-mask adaptation improved AUC and true acceptance rate (TAR) but did not restore the nominal FAR, and replacing the detection–alignment path changed AUC substantially while leaving FAR nearly unchanged. Recalibration with 25–100 target identities lowered median FAR, but optimistic independent-pair upper bounds at the median split were ≤1% in only 4 of 12 settings, so near-target results remain uncertain. In an exploratory fixed-holdout analysis, unmasked calibration was conservative, whereas condition-matched calibration recovered TAR but left FAR near the target. Within the tested protocols, the results indicate that recognition accuracy and decision-threshold robustness should be evaluated separately and that deployment requires site-specific threshold validation.

Authors

Institutions

Publication Details

Journal
Sensors
Published
2026-11-17
DOI
https://doi.org/10.3390/s26227234
Primary Topic
Face recognition and analysis
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Decision-Threshold Transferability and Robustness in Masked Face Verification

Goo-Man Park, Jisang Lee
2 links
Sensors
Face recognition and analysis
article

Decision-Threshold Transferability and Robustness in Masked Face Verification

Goo-Man Park, Jisang Lee
article en

Abstract

Masked-face verification systems apply decision thresholds set on development data, but whether these keep their target false acceptance rate (FAR) after deployment is rarely tested. We transferred thresholds set at 0.1% and 1% FAR on synthetically masked LFW to two external masked-face datasets, RMFDVER and the mixed-provenance COMASK20, using two ArcFace/MS1M-pretrained models and identity-level bootstrapping. At the 1% target, the observed FAR rose to 2.5–2.8% on RMFDVER and 16–21% on COMASK20. FAR inflation also occurred for reconstructed unmasked comparisons, and transfer between the external datasets was either too permissive or too strict. Model replacement and synthetic-mask adaptation improved AUC and true acceptance rate (TAR) but did not restore the nominal FAR, and replacing the detection–alignment path changed AUC substantially while leaving FAR nearly unchanged. Recalibration with 25–100 target identities lowered median FAR, but optimistic independent-pair upper bounds at the median split were ≤1% in only 4 of 12 settings, so near-target results remain uncertain. In an exploratory fixed-holdout analysis, unmasked calibration was conservative, whereas condition-matched calibration recovered TAR but left FAR near the target. Within the tested protocols, the results indicate that recognition accuracy and decision-threshold robustness should be evaluated separately and that deployment requires site-specific threshold validation.

SensorsVol. 26(22)
Seoul National University of Science and Technology (KR)
Face recognition and analysis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon