# Empirically Analyzing the Effect of Dataset Biases on Deep Face Recognition Systems

arXiv: https://arxiv.org/abs/1712.01619 · HTML: https://mlsanity.com/paper/1712.01619/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Dec 2017.

## Built on by (most cited first, 28 of 28)

- [Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers](https://mlsanity.com/paper/2203.04913/) (2022)
- [Discover the Unknown Biased Attribute of an Image Classifier](https://mlsanity.com/paper/2104.14556/) (2021)
- [OOD-CV: A Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Images](https://mlsanity.com/paper/2111.14341/) (2021)
- [SCAMPS: Synthetics for Camera Measurement of Physiological Signals](https://mlsanity.com/paper/2206.04197/) (2022)
- [Synthetic Data in Human Analysis: A Survey](https://mlsanity.com/paper/2208.09191/) (2022)
- [Controllable Inversion of Black-Box Face Recognition Models via Diffusion](https://mlsanity.com/paper/2303.13006/) (2023)
- [On Modality Bias Recognition and Reduction](https://mlsanity.com/paper/2202.12690/) (2022)
- [Ethical Considerations for Responsible Data Curation](https://mlsanity.com/paper/2302.03629/) (2023)
- [AI-Generated Images as Data Source: The Dawn of Synthetic Era](https://mlsanity.com/paper/2310.01830/) (2023)
- [OOD-CV-v2: An extended Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Images](https://mlsanity.com/paper/2304.10266/) (2023)
- [A Deep Dive into Dataset Imbalance and Bias in Face Identification](https://mlsanity.com/paper/2203.08235/) (2022)
- [Explaining Deep Convolutional Neural Networks via Latent Visual-Semantic Filter Attention](https://mlsanity.com/paper/2204.04601/) (2022)
- [Simulated Adversarial Testing of Face Recognition Models](https://mlsanity.com/paper/2106.04569/) (2021)
- [PoseExaminer: Automated Testing of Out-of-Distribution Robustness in Human Pose and Shape Estimation](https://mlsanity.com/paper/2303.07337/) (2023)
- [Synthetic Data for Multi-Parameter Camera-Based Physiological Sensing](https://mlsanity.com/paper/2110.04902/) (2021)
- [Causality-Inspired Taxonomy for Explainable Artificial Intelligence](https://mlsanity.com/paper/2208.09500/) (2022)
- [The Impact of Racial Distribution in Training Data on Face Recognition Bias: A Closer Look](https://mlsanity.com/paper/2211.14498/) (2022)
- [Finding Differences Between Transformers and ConvNets Using Counterfactual Simulation Testing](https://mlsanity.com/paper/2211.16499/) (2022)
- [Matched sample selection with GANs for mitigating attribute confounding](https://mlsanity.com/paper/2103.13455/) (2021)
- [Human Body Measurement Estimation with Adversarial Augmentation](https://mlsanity.com/paper/2210.05667/) (2022)
- [A Bayesian Approach to OOD Robustness in Image Classification](https://mlsanity.com/paper/2403.07277/) (2024)
- [Towards Inclusive HRI: Using Sim2Real to Address Underrepresentation in Emotion Expression Recognition](https://mlsanity.com/paper/2208.07472/) (2022)
- [CounterFace: A Synthetic Face Dataset for Fine-Grained Counterfactual Evaluation of Face Recognition Systems](https://mlsanity.com/paper/2407.13922/) (2024)
- [Facing Asymmetry -- Uncovering the Causal Link between Facial Symmetry and Expression Classifiers using Synthetic Interventions](https://mlsanity.com/paper/2409.15927/) (2024)
- [Linking convolutional kernel size to generalization bias in face analysis CNNs](https://mlsanity.com/paper/2302.03750/) (2023)
- [GELDA: A generative language annotation framework to reveal visual biases in datasets](https://mlsanity.com/paper/2311.18064/) (2023)
- [BelHouse3D: A Benchmark Dataset for Assessing Occlusion Robustness in 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2411.13251/) (2024)
- [Mask-up: Investigating Biases in Face Re-identification for Masked Faces](https://mlsanity.com/paper/2402.13771/) (2024)

## Abstract (arXiv)

It is unknown what kind of biases modern in the wild face datasets have because of their lack of annotation. A direct consequence of this is that total recognition rates alone only provide limited insight about the generalization ability of a Deep Convolutional Neural Networks (DCNNs). We propose to empirically study the effect of different types of dataset biases on the generalization ability of DCNNs. Using synthetically generated face images, we study the face recognition rate as a function of interpretable parameters such as face pose and light. The proposed method allows valuable details about the generalization performance of different DCNN architectures to be observed and compared. In our experiments, we find that: 1) Indeed, dataset bias has a significant influence on the generalization performance of DCNNs. 2) DCNNs can generalize surprisingly well to unseen illumination conditions and large sampling gaps in the pose variation. 3) Using the presented methodology we reveal that the VGG-16 architecture outperforms the AlexNet architecture at face recognition tasks because it can much better generalize to unseen face poses, although it has significantly more parameters. 4) We uncover a main limitation of current DCNN architectures, which is the difficulty to generalize when different identities to not share the same pose variation. 5) We demonstrate that our findings on synthetic data also apply when learning from real-world data. Our face image generator is publicly available to enable the community to benchmark other DCNN architectures.