Analyzing and reducing the damage of dataset bias to face recognition with synthetic data
Kortylewski A, Egger B, Schneider A, Gerig T, Morel-Forster A, Vetter T (2019)
Publication Type: Conference contribution
Publication year: 2019
Publisher: IEEE Computer Society
Book Volume: 2019-June
Pages Range: 2261-2268
Conference Proceedings Title: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Event location: Long Beach, CA
ISBN: 9781728125060
Abstract
It is well known that deep learning approaches to face recognition suffer from various biases in the available training data. In this work, we demonstrate the large potential of synthetic data for analyzing and reducing the negative effects of dataset bias on deep face recognition systems. In particular we explore two complementary application areas for synthetic face images: 1) Using fully annotated synthetic face images we can study the face recognition rate as a function of interpretable parameters such as face pose. This enables us to systematically analyze the effect of different types of dataset biases on the generalization ability of neural network architectures. Our analysis reveals that deeper neural network architectures can generalize better to unseen face poses. Furthermore, our study shows that current neural network architectures cannot disentangle face pose and facial identity, which limits their generalization ability. 2) We pre-train neural networks with large-scale synthetic data that is highly variable in face pose and the number of facial identities. After a subsequent fine-tuning with real-world data, we observe that the damage of dataset bias in the real-world data is largely reduced. Furthermore, we demonstrate that the size of real-world datasets can be reduced by 75% while maintaining competitive face recognition performance. The data and software used in this work are publicly available.
Authors with CRIS profile
Involved external institutions
Switzerland (CH)How to cite
APA:
Kortylewski, A., Egger, B., Schneider, A., Gerig, T., Morel-Forster, A., & Vetter, T. (2019). Analyzing and reducing the damage of dataset bias to face recognition with synthetic data. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (pp. 2261-2268). Long Beach, CA, US: IEEE Computer Society.
MLA:
Kortylewski, Adam, et al. "Analyzing and reducing the damage of dataset bias to face recognition with synthetic data." Proceedings of the 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019, Long Beach, CA IEEE Computer Society, 2019. 2261-2268.
BibTeX: Download