# Low-Quality Face Recognition using Center Aligned Representations and Local Margin Constraints

arXiv: https://arxiv.org/abs/2609.01014 · HTML: https://mlsanity.com/paper/2609.01014/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 47 of its 70 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Builds on (most cited first, 30 of 47)

- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [DoRA: Weight-Decomposed Low-Rank Adaptation](https://mlsanity.com/paper/2402.09353/) (2024)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition](https://mlsanity.com/paper/1607.08221/) (2016)
- [Deep Domain Confusion: Maximizing for Domain Invariance](https://mlsanity.com/paper/1412.3474/) (2014)
- [Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels](https://mlsanity.com/paper/2312.17090/) (2023)
- [Learning Face Representation from Scratch](https://mlsanity.com/paper/1411.7923/) (2014)
- [AdaFace: Quality Adaptive Margin for Face Recognition](https://mlsanity.com/paper/2204.00964/) (2022)
- [MagFace: A Universal Representation for Face Recognition and Quality Assessment](https://mlsanity.com/paper/2103.06627/) (2021)
- [CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition](https://mlsanity.com/paper/2004.00288/) (2020)
- [PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models](https://mlsanity.com/paper/2404.02948/) (2024)
- [Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments](https://mlsanity.com/paper/1708.08197/) (2017)
- [WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2103.04098/) (2021)
- [Partial FC: Training 10 Million Identities on a Single Machine](https://mlsanity.com/paper/2010.05222/) (2020)
- [Convolutional Bypasses Are Better Vision Transformer Adapters](https://mlsanity.com/paper/2207.07039/) (2022)
- [SER-FIQ: Unsupervised Estimation of Face Image Quality Based on Stochastic Embedding Robustness](https://mlsanity.com/paper/2003.09373/) (2020)
- [Neural Collapse: A Review on Modelling Principles and Generalization](https://mlsanity.com/paper/2206.04041/) (2022)
- [Beyond Sharing Weights for Deep Domain Adaptation](https://mlsanity.com/paper/1603.06432/) (2016)
- [CR-FIQA: Face Image Quality Assessment by Learning Sample Relative Classifiability](https://mlsanity.com/paper/2112.06592/) (2021)
- [Low-Resolution Face Recognition](https://mlsanity.com/paper/1811.08965/) (2018)
- [Expanding Accurate Person Recognition to New Altitudes and Ranges: The BRIAR Dataset](https://mlsanity.com/paper/2211.01917/) (2022)
- [Super-Identity Convolutional Neural Network for Face Hallucination](https://mlsanity.com/paper/1811.02328/) (2018)
- [Continual Representation Learning for Biometric Identification](https://mlsanity.com/paper/2006.04455/) (2020)
- [Teaching Where to Look: Attention Similarity Knowledge Distillation for Low Resolution Face Recognition](https://mlsanity.com/paper/2209.14498/) (2022)
- [FAN: Feature Adaptation Network for Surveillance Face Recognition and Normalization](https://mlsanity.com/paper/1911.11680/) (2019)

## Abstract (arXiv)

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 github.com/candllq/nam.