EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

RCF-Face: Risk-Calibrated Factorization for Lightweight Face Verification Under Composite Disturbances

Yanhao Shen, Zhibin Zhao, Yalong Meng

Electronics · 06.06.2026 · 15 (12) · 2497

DOI: 10.3390/electronics15122497 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 06.06.2026. Verfasst von Yanhao Shen und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Compact face verifiers at access-control and surveillance terminals must operate under specular reflection, off-frontal pose, and mask occlusion, disturbances that frequently co-occur in practice. Existing objectives optimize identity discrimination and score-threshold reliability separately. As a result, disturbance cues leak into the identity embedding and inflate the impostor-score tail near the operating false-acceptance rate (FAR)—a structural weakness that backbone scaling alone does not resolve within a fixed parameter budget. We propose RCF-Face, a 1.12 M-parameter verifier for the sub-2 M-parameter, sub-0.2 GFLOP budget of Ampere-class edge GPUs, trained under a unified objective that combines representation-level leakage suppression (HSIC-based identity–disturbance factorization with augmentation-based counterfactual consistency) and decision-level score shaping via a softplus tail-risk penalty anchored to the target FAR. Across four disturbance-focused protocols (CFP-FP, IJB-C, RMFRD, and a reflection-augmented subset), RCF-Face reaches a Composite-Disturbance Score (CDS, the mean verification accuracy over the four protocols) of 89.05 at 0.166 GFLOPs, improving on the capacity-matched AdaFace-Lite baseline by 4.67 percentage points, with both per-protocol gains over this baseline significant under Bonferroni correction. Zero-shot evaluation on two open-source reflection-related datasets (SoF and MeGlass) shows that the robustness gains transfer to real-world images, although these datasets isolate single disturbance axes and do not constitute a composite-disturbance benchmark. On a Jetson Orin NX 16 GB, batch-1 latency is 2.41 ms (FP16) and 1.66 ms (INT8), supporting Ampere-class edge-GPU deployment.

Zitieren

APA

Shen, Y., Zhao, Z., & Meng, Y. (2026). RCF-Face: Risk-Calibrated Factorization for Lightweight Face Verification Under Composite Disturbances. Electronics, 15(12), 2497. https://doi.org/10.3390/electronics15122497

Vancouver

Shen Y, Zhao Z, Meng Y. RCF-Face: Risk-Calibrated Factorization for Lightweight Face Verification Under Composite Disturbances. Electronics. 2026;15(12):2497. doi:10.3390/electronics15122497

BibTeX
@article{Shen2026,
  author = {Shen, Yanhao and Zhao, Zhibin and Meng, Yalong},
  title = {RCF-Face: Risk-Calibrated Factorization for Lightweight Face Verification Under Composite Disturbances},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {12},
  pages = {2497},
  doi = {10.3390/electronics15122497}
}
Kostenlos starten →