EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-SA 4.0

EfficientNet-Lite

Sheerko R. HmaSalah, Abdulbasit K. Al-Talabani, Aras T. Asaad

ARO-THE SCIENTIFIC JOURNAL OF KOYA UNIVERSITY · 04.11.2026 · 14 (2) · 112-120

DOI: 10.14500/aro.12990 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ARO-THE SCIENTIFIC JOURNAL OF KOYA UNIVERSITY, online erschienen am 04.11.2026. Verfasst von Sheerko R. HmaSalah und 2 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).

AbstractBibliografische AngabenZitieren

Abstract (Originalsprache)

Morphing attacks on facial images pose a serious threat to face recognition systems during identity verification. In this paper, we introduce a parameter-efficient family of convolutional neural networks, named EfficientNet-Lite (EN_Lite), for morph attack detection (MAD). The experimental framework uses eight datasets, four morph generation methods, and ten homogeneous and heterogeneous evaluation scenarios under a leave-one-datasetout protocol. Performance was assessed using dataset-size-weighted average equal error rate (EERWA ), computed across the held-out datasets within each scenario. EN_Lite was evaluated using ImageNet1K and VGGFace2-HQ pre-training, with the latter comprising 1,107,817 successfully processed facial images. The ImageNetpretrained IEN_Lite-1 achieved a mean EERWA of 2.99%, compared with 2.65% for EfficientNet-B3 while using approximately 76% fewer parameters. It also achieved a lower mean EERWA than GhostNet-1.0x (4.01%), MobileNetV3-Large (5.03%), MobileNetV3-Small (6.03%), and ShuffleNet V2 (5.31%). The VGGFace2-HQ-pretrained variants produced higher error rates than their corresponding ImageNet-pretrained variants under the evaluated protocol. Performance remained strong in homogeneous scenarios but degraded under heterogeneous cross-morph evaluation. Overall, EN_Lite provides a favorable efficiency–performance trade-off for MAD, while high-security deployment should be assessed at application-specific operating points.

Zitieren

APA

HmaSalah, S. R., Al-Talabani, A. K., & Asaad, A. T. (2026). EfficientNet-Lite. ARO-THE SCIENTIFIC JOURNAL OF KOYA UNIVERSITY, 14(2), 112-120. https://doi.org/10.14500/aro.12990

Vancouver

HmaSalah SR, Al-Talabani AK, Asaad AT. EfficientNet-Lite. ARO-THE SCIENTIFIC JOURNAL OF KOYA UNIVERSITY. 2026;14(2):112-120. doi:10.14500/aro.12990

BibTeX
@article{HmaSalah2026,
  author = {HmaSalah, Sheerko R. and Al-Talabani, Abdulbasit K. and Asaad, Aras T.},
  title = {EfficientNet-Lite},
  journal = {ARO-THE SCIENTIFIC JOURNAL OF KOYA UNIVERSITY},
  year = {2026},
  volume = {14},
  number = {2},
  pages = {112--120},
  doi = {10.14500/aro.12990}
}
Kostenlos starten →