Metraipolis › archive › dc_d72cbdec3ff9

Low-Quality Face Recognition using Center Aligned Representations and Local Margin Constraints — arXiv:2609.01014

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.01014
License (as archived): CC0-1.0
Archived: 2026-10-17T07:13:46.334Z
SHA-256 of the archived text: 2c50562f99c1923e6b79d35975fdc0b3357d3065b9c3529beb3f302c72d56108
Stable URL of this page: https://metraipolis.com/documento/dc_d72cbdec3ff9

How to cite

Low-Quality Face Recognition using Center Aligned Representations and Local Margin Constraints — arXiv:2609.01014 — arXiv (en), https://arxiv.org/abs/2609.01014 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d72cbdec3ff9 (Metraipolis archive dc_d72cbdec3ff9, sha256 2c50562f99c1923e6b79d35975fdc0b3357d3065b9c3529beb3f302c72d56108)

BibTeX

@misc{dcd72cbdec3ff9,
  title = {Low-Quality Face Recognition using Center Aligned Representations and Local Margin Constraints — arXiv:2609.01014},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.01014},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d72cbdec3ff9; sha256 2c50562f99c1923e6b79d35975fdc0b3357d3065b9c3529beb3f302c72d56108},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01014. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Low-quality face recognition (LQFR) remains challenging due to the difficulty of matching degraded query (probe) images against low-quality (LQ) enrollment (gallery) imagery and the scarcity of training data for large-scale models. While recent face recognition (FR) models perform well on high-quality (HQ) imagery, their accuracy drops significantly on LQ images with extremely low signal-to-noise ratio (SNR). Moreover, fine-tuning HQ-pretrained models on LQ data often improves LQ recognition at the expense of HQ generalization. This trade-off becomes more pronounced in modern evaluation settings spanning multiple datasets with varying image quality levels. To address these limitations, we propose a unified framework that combines three main components: (1) Local Probability Margin (LPM), which estimates per-sample difficulty directly from the model's discriminative landscape; (2) Nested Attention Module (NAM), a new low-rank adapter module that embeds a self-attention mechanism within selected transformer layers; and (3) Quality Gating Protocol (QGP), where an off-the-shelf image quality estimator modulates the adapter contribution at test time, enabling a single model to handle the full quality spectrum without sacrificing HQ performance. Experiments on surveillance (TinyFace, SurvFace) and standard (IJB-B, IJB-C) face recognition benchmarks demonstrate consistent gains in both identification and verification. Code and models will be released at this http URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-02 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.01014 — 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 2026-10-17T07:00:58.959Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).