# Analyzing the Impact of Shape & Context on the Face Recognition Performance of Deep Networks

arXiv: https://arxiv.org/abs/2208.02991 · HTML: https://mlsanity.com/paper/2208.02991/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 57 references that are in the map.
- First posted on arXiv 5 Aug 2022.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition](https://mlsanity.com/paper/1607.08221/) (2016)
- [Learning Face Representation from Scratch](https://mlsanity.com/paper/1411.7923/) (2014)
- [Deep Face Recognition: A Survey](https://mlsanity.com/paper/1804.06655/) (2018)
- [Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning](https://mlsanity.com/paper/2004.11660/) (2020)
- [The MegaFace Benchmark: 1 Million Faces for Recognition at Scale](https://mlsanity.com/paper/1512.00596/) (2015)
- [A Light CNN for Deep Face Representation with Noisy Labels](https://mlsanity.com/paper/1511.02683/) (2015)
- [Context-Aware Emotion Recognition Networks](https://mlsanity.com/paper/1908.05913/) (2019)
- [A Comprehensive Study on Face Recognition Biases Beyond Demographics](https://mlsanity.com/paper/2103.01592/) (2021)
- [Improved Mixed-Example Data Augmentation](https://mlsanity.com/paper/1805.11272/) (2018)
- [This Face Does Not Exist ... But It Might Be Yours! Identity Leakage in Generative Models](https://mlsanity.com/paper/2101.05084/) (2020)
- [A Survey on Face Data Augmentation](https://mlsanity.com/paper/1904.11685/) (2019)
- [Do We Really Need to Collect Millions of Faces for Effective Face Recognition?](https://mlsanity.com/paper/1603.07057/) (2016)
- [The Do's and Don'ts for CNN-based Face Verification](https://mlsanity.com/paper/1705.07426/) (2017)
- [SREFI: Synthesis of Realistic Example Face Images](https://mlsanity.com/paper/1704.06693/) (2017)
- [Fast Face Image Synthesis with Minimal Training](https://mlsanity.com/paper/1811.01474/) (2018)
- [LEGAN: Disentangled Manipulation of Directional Lighting and Facial Expressions by Leveraging Human Perceptual Judgements](https://mlsanity.com/paper/2010.01464/) (2020)

## Built on by (most cited first, 1 of 1)

- [Evaluating Contextual Bias in CNN Image Classification: Evidence from Agricultural Benchmark Datasets](https://mlsanity.com/paper/2609.14654/) (2026)

## Abstract (arXiv)

In this article, we analyze how changing the underlying 3D shape of the base identity in face images can distort their overall appearance, especially from the perspective of deep face recognition. As done in popular training data augmentation schemes, we graphically render real and synthetic face images with randomly chosen or best-fitting 3D face models to generate novel views of the base identity. We compare deep features generated from these images to assess the perturbation these renderings introduce into the original identity. We perform this analysis at various degrees of facial yaw with the base identities varying in gender and ethnicity. Additionally, we investigate if adding some form of context and background pixels in these rendered images, when used as training data, further improves the downstream performance of a face recognition model. Our experiments demonstrate the significance of facial shape in accurate face matching and underpin the importance of contextual data for network training.