# Attributes Shape the Embedding Space of Face Recognition Models

arXiv: https://arxiv.org/abs/2507.11372 · HTML: https://mlsanity.com/paper/2507.11372/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 40 references that are in the map.
- First posted on arXiv 15 Jul 2025.

## Builds on (most cited first, 22 of 22)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [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)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [AdaFace: Quality Adaptive Margin for Face Recognition](https://mlsanity.com/paper/2204.00964/) (2022)
- [Additive Margin Softmax for Face Verification](https://mlsanity.com/paper/1801.05599/) (2018)
- [Convergent Learning: Do different neural networks learn the same representations?](https://mlsanity.com/paper/1511.07543/) (2015)
- [Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning](https://mlsanity.com/paper/2105.15134/) (2021)
- [Arc2Face: A Foundation Model for ID-Consistent Human Faces](https://mlsanity.com/paper/2403.11641/) (2024)
- [GAN-Control: Explicitly Controllable GANs](https://mlsanity.com/paper/2101.02477/) (2021)
- [CONFIG: Controllable Neural Face Image Generation](https://mlsanity.com/paper/2005.02671/) (2020)
- [Towards Interpretable Face Recognition](https://mlsanity.com/paper/1805.00611/) (2018)
- [xCos: An Explainable Cosine Metric for Face Verification Task](https://mlsanity.com/paper/2003.05383/) (2020)
- [SphereFace Revived: Unifying Hyperspherical Face Recognition](https://mlsanity.com/paper/2109.05565/) (2021)
- [Deep Convolutional Neural Networks in the Face of Caricature: Identity and Image Revealed](https://mlsanity.com/paper/1812.10902/) (2018)
- [Triplet Probabilistic Embedding for Face Verification and Clustering](https://mlsanity.com/paper/1604.05417/) (2016)
- [LARNet: Lie Algebra Residual Network for Face Recognition](https://mlsanity.com/paper/2103.08147/) (2021)
- [TopoFR: A Closer Look at Topology Alignment on Face Recognition](https://mlsanity.com/paper/2410.10587/) (2024)
- [Face Attributes as Cues for Deep Face Recognition Understanding](https://mlsanity.com/paper/2105.07054/) (2021)
- [Masked Face Recognition with Generative-to-Discriminative Representations](https://mlsanity.com/paper/2405.16761/) (2024)

## Built on by (most cited first, 4 of 4)

- [A solution to generalized learning from small training sets found in infants repeated visual experiences of individual objects](https://mlsanity.com/paper/2510.15060/) (2025)
- [Casting the Net! Revisiting MasterFace Impersonation Attacks](https://mlsanity.com/paper/2608.06952/) (2026)
- [SCOUT: Semantic Concept Discovery for Open-Vocabulary Editing of face Recognition Templates](https://mlsanity.com/paper/2608.16251/) (2026)
- [EXPL-FR: Explaining Face Recognition Models via Vision-Language Alignment](https://mlsanity.com/paper/2608.21486/) (2026)

## Abstract (arXiv)

Face Recognition (FR) tasks have made significant progress with the advent of Deep Neural Networks, particularly through margin-based triplet losses that embed facial images into high-dimensional feature spaces. During training, these contrastive losses focus exclusively on identity information as labels. However, we observe a multiscale geometric structure emerging in the embedding space, influenced by interpretable facial (e.g., hair color) and image attributes (e.g., contrast). We propose a geometric approach to describe the dependence or invariance of FR models to these attributes and introduce a physics-inspired alignment metric. We evaluate the proposed metric on controlled, simplified models and widely used FR models fine-tuned with synthetic data for targeted attribute augmentation. Our findings reveal that the models exhibit varying degrees of invariance across different attributes, providing insight into their strengths and weaknesses and enabling deeper interpretability. Code available here: https://github.com/mantonios107/attrs-fr-embs}{https://github.com/mantonios107/attrs-fr-embs