# Boosting Deep Face Recognition via Disentangling Appearance and Geometry

arXiv: https://arxiv.org/abs/2001.04559 · HTML: https://mlsanity.com/paper/2001.04559/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jan 2020.

## Built on by (most cited first, 5 of 5)

- [Deep GAN-Based Cross-Spectral Cross-Resolution Iris Recognition](https://mlsanity.com/paper/2108.01569/) (2021)
- [Zero-shot racially balanced dataset generation using an existing biased StyleGAN2](https://mlsanity.com/paper/2305.07710/) (2023)
- [Prototype Memory for Large-scale Face Representation Learning](https://mlsanity.com/paper/2105.02103/) (2021)
- [Profile to Frontal Face Recognition in the Wild Using Coupled Conditional GAN](https://mlsanity.com/paper/2107.13742/) (2021)
- [Fair GANs through model rebalancing for extremely imbalanced class distributions](https://mlsanity.com/paper/2308.08638/) (2023)

## Abstract (arXiv)

In this paper, we propose a framework for disentangling the appearance and geometry representations in the face recognition task. To provide supervision for this aim, we generate geometrically identical faces by incorporating spatial transformations. We demonstrate that the proposed approach enhances the performance of deep face recognition models by assisting the training process in two ways. First, it enforces the early and intermediate convolutional layers to learn more representative features that satisfy the properties of disentangled embeddings. Second, it augments the training set by altering faces geometrically. Through extensive experiments, we demonstrate that integrating the proposed approach into state-of-the-art face recognition methods effectively improves their performance on challenging datasets, such as LFW, YTF, and MegaFace. Both theoretical and practical aspects of the method are analyzed rigorously by concerning ablation studies and knowledge transfer tasks. Furthermore, we show that the knowledge leaned by the proposed method can favor other face-related tasks, such as attribute prediction.