Metraipolis › archive › dc_6e59833ca2da
A Comparative Transfer-Learning Study of CNN Backbones for Partial Face Recognition on the SoF Dataset — arXiv:2609.31677
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.31677
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T20:59:21.862Z
- SHA-256 of the archived text
2f7512de87bcc5a983383b5c5ced627985a58739198d7baa40eb7df2f97d0f31- Stable URL of this page
https://metraipolis.com/documento/dc_6e59833ca2da
How to cite
A Comparative Transfer-Learning Study of CNN Backbones for Partial Face Recognition on the SoF Dataset — arXiv:2609.31677 — arXiv (en), https://arxiv.org/abs/2609.31677 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6e59833ca2da (Metraipolis archive dc_6e59833ca2da, sha256 2f7512de87bcc5a983383b5c5ced627985a58739198d7baa40eb7df2f97d0f31)
BibTeX
@misc{dc6e59833ca2da,
title = {A Comparative Transfer-Learning Study of CNN Backbones for Partial Face Recognition on the SoF Dataset — arXiv:2609.31677},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.31677},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6e59833ca2da; sha256 2f7512de87bcc5a983383b5c5ced627985a58739198d7baa40eb7df2f97d0f31},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31677. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Face recognition is widely deployed in surveillance, access control, and forensic workflows, yet accuracy degrades sharply once the face is occluded by accessories, foreground objects, or the frame edge. Because most faces in the wild are partial, robust partial face recognition (PFR) remains open. This paper compares three pretrained convolutional backbones, ResNet-50, VGG-16, and FaceNet, fine-tuned for PFR by transfer learning under identical preprocessing, splitting, and optimization protocols on the Specs-on-Faces (SoF) dataset. All three arms use a common 160x160 input and a frozen backbone with a trainable head under a fixed epoch budget and no per-backbone hyperparameter search. The FaceNet configuration, denoted PFN (Partial FaceNet), substantially outperforms the other two, reaching 97.4% test accuracy with macro-averaged 87.04% precision, 84.61% recall, and 84.17% F1 over the 112 identity classes, the highest accuracy and recall reported on SoF. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.31677 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T20:29:02.022Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).