# Quality-Aware Prototype Memory for Face Representation Learning

arXiv: https://arxiv.org/abs/2311.07734 · HTML: https://mlsanity.com/paper/2311.07734/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 59 references that are in the map.
- First posted on arXiv 13 Nov 2023.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [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)
- [Deep Face Recognition: A Survey](https://mlsanity.com/paper/1804.06655/) (2018)
- [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)
- [The MegaFace Benchmark: 1 Million Faces for Recognition at Scale](https://mlsanity.com/paper/1512.00596/) (2015)
- [Partial FC: Training 10 Million Identities on a Single Machine](https://mlsanity.com/paper/2010.05222/) (2020)
- [ElasticFace: Elastic Margin Loss for Deep Face Recognition](https://mlsanity.com/paper/2109.09416/) (2021)
- [Face Image Quality Assessment: A Literature Survey](https://mlsanity.com/paper/2009.01103/) (2020)
- [Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC](https://mlsanity.com/paper/2203.15565/) (2022)
- [CR-FIQA: Face Image Quality Assessment by Learning Sample Relative Classifiability](https://mlsanity.com/paper/2112.06592/) (2021)
- [YOLO5Face: Why Reinventing a Face Detector](https://mlsanity.com/paper/2105.12931/) (2021)
- [Cross-Quality LFW: A Database for Analyzing Cross-Resolution Image Face Recognition in Unconstrained Environments](https://mlsanity.com/paper/2108.10290/) (2021)
- [The Elements of End-to-end Deep Face Recognition: A Survey of Recent Advances](https://mlsanity.com/paper/2009.13290/) (2020)
- [QMagFace: Simple and Accurate Quality-Aware Face Recognition](https://mlsanity.com/paper/2111.13475/) (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)
- [A Quality Aware Sample-to-Sample Comparison for Face Recognition](https://mlsanity.com/paper/2306.04000/) (2023)
- [Recognizability Embedding Enhancement for Very Low-Resolution Face Recognition and Quality Estimation](https://mlsanity.com/paper/2304.10066/) (2023)
- [Softmax Dissection: Towards Understanding Intra- and Inter-class Objective for Embedding Learning](https://mlsanity.com/paper/1908.01281/) (2019)
- [Towards Flops-constrained Face Recognition](https://mlsanity.com/paper/1909.00632/) (2019)
- [Recognizing Disguised Faces in the Wild](https://mlsanity.com/paper/1811.08837/) (2018)
- [Harnessing Unrecognizable Faces for Improving Face Recognition](https://mlsanity.com/paper/2106.04112/) (2021)
- [STC speaker recognition systems for the NIST SRE 2021](https://mlsanity.com/paper/2111.02298/) (2021)
- [State of the Art of Quality Assessment of Facial Images](https://mlsanity.com/paper/2211.08030/) (2022)
- [Assessing Bias in Face Image Quality Assessment](https://mlsanity.com/paper/2211.15265/) (2022)
- [Optimization-Based Improvement of Face Image Quality Assessment Techniques](https://mlsanity.com/paper/2305.14856/) (2023)

## Abstract (arXiv)

Prototype Memory is a powerful model for face representation learning. It enables training face recognition models on datasets of any size by generating prototypes (classifier weights) on the fly and efficiently utilizing them. Prototype Memory demonstrated strong results in many face recognition benchmarks. However, the algorithm of prototype generation, used in it, is prone to the problems of imperfectly calculated prototypes in case of low-quality or poorly recognizable faces in the images, selected for the prototype creation. All images of the same person presented in the mini-batch are used with equal weights, and the resulting averaged prototype can be contaminated by imperfect embeddings of low-quality face images. This may lead to misleading training signals and degrade the performance of the trained models. In this paper, we propose a simple and effective way to improve Prototype Memory with quality-aware prototype generation. Quality-Aware Prototype Memory uses different weights for images of different quality in the process of prototype generation. With this improvement, prototypes receive more informative signals from high-quality images and are less affected by low-quality ones. We propose and compare several methods of quality estimation and usage, perform extensive experiments on the different face recognition benchmarks and demonstrate the advantages of the proposed model compared to the basic version of Prototype Memory.