# PreFIQs: Face Image Quality Is What Survives Pruning

arXiv: https://arxiv.org/abs/2605.13396 · HTML: https://mlsanity.com/paper/2605.13396/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 49 references that are in the map.
- First posted on arXiv 13 May 2026.

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition](https://mlsanity.com/paper/1607.08221/) (2016)
- [Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks](https://mlsanity.com/paper/2102.00554/) (2021)
- [Pruning neural networks without any data by iteratively conserving synaptic flow](https://mlsanity.com/paper/2006.05467/) (2020)
- [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)
- [Pruning and Quantization for Deep Neural Network Acceleration: A Survey](https://mlsanity.com/paper/2101.09671/) (2021)
- [Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments](https://mlsanity.com/paper/1708.08197/) (2017)
- [DepGraph: Towards Any Structural Pruning](https://mlsanity.com/paper/2301.12900/) (2023)
- [What Do Compressed Deep Neural Networks Forget?](https://mlsanity.com/paper/1911.05248/) (2019)
- [ElasticFace: Elastic Margin Loss for Deep Face Recognition](https://mlsanity.com/paper/2109.09416/) (2021)
- [SER-FIQ: Unsupervised Estimation of Face Image Quality Based on Stochastic Embedding Robustness](https://mlsanity.com/paper/2003.09373/) (2020)
- [CR-FIQA: Face Image Quality Assessment by Learning Sample Relative Classifiability](https://mlsanity.com/paper/2112.06592/) (2021)
- [SDD-FIQA: Unsupervised Face Image Quality Assessment with Similarity Distribution Distance](https://mlsanity.com/paper/2103.05977/) (2021)
- [Self-Damaging Contrastive Learning](https://mlsanity.com/paper/2106.02990/) (2021)
- [Biometric Quality: Review and Application to Face Recognition with FaceQnet](https://mlsanity.com/paper/2006.03298/) (2020)
- [Cross-Quality LFW: A Database for Analyzing Cross-Resolution Image Face Recognition in Unconstrained Environments](https://mlsanity.com/paper/2108.10290/) (2021)
- [DifFIQA: Face Image Quality Assessment Using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2305.05768/) (2023)
- [FaceQAN: Face Image Quality Assessment Through Adversarial Noise Exploration](https://mlsanity.com/paper/2212.02127/) (2022)
- [DSL-FIQA: Assessing Facial Image Quality via Dual-Set Degradation Learning and Landmark-Guided Transformer](https://mlsanity.com/paper/2406.09622/) (2024)
- [Considerations on the Evaluation of Biometric Quality Assessment Algorithms](https://mlsanity.com/paper/2303.13294/) (2023)
- [A Deep Insight into Measuring Face Image Utility with General and Face-specific Image Quality Metrics](https://mlsanity.com/paper/2110.11111/) (2021)
- [GraFIQs: Face Image Quality Assessment Using Gradient Magnitudes](https://mlsanity.com/paper/2404.12203/) (2024)
- [Inducing Predictive Uncertainty Estimation for Face Recognition](https://mlsanity.com/paper/2009.00603/) (2020)
- [ViT-FIQA: Assessing Face Image Quality using Vision Transformers](https://mlsanity.com/paper/2508.13957/) (2025)
- [FROQ: Observing Face Recognition Models for Efficient Quality Assessment](https://mlsanity.com/paper/2509.17689/) (2025)

## Abstract (arXiv)

Face Image Quality Assessment (FIQA) evaluates the utility of a face image for automated face recognition (FR) systems. In this work, we propose PreFIQs, an unsupervised and training-free FIQA framework grounded in the Pruning Identified Exemplar (PIE) hypothesis. We hypothesize that low-utility face images rely disproportionately on fragile network parameters, resulting in larger geometric displacement of their embeddings under model sparsification. Accordingly, PreFIQs quantifies image utility as the Euclidean distance between L2-normalized embeddings extracted from a pre-trained FR model and its pruned counterpart. We provide a first-order theoretical justification via a Jacobian-vector product analysis, demonstrating that this empirical drift serves as a computationally efficient approximation of the exact geometric sensitivity of the latent embedding manifold. Extensive experiments across eight benchmarks and four FR models demonstrate that PreFIQs achieves competitive or superior performance compared to state-of-the-art FIQA methods, including establishing new state-of-the-art results on several benchmarks, without any training or supervision. These results validate parameter sparsification as a principled and practically efficient signal for face image utility, and demonstrate that quality is, in essence, what survives pruning.