An Assessment of GANs for Identity-related Applications

TL;DR

This paper evaluates the ability of GANs to generate unique identities and disentangle identity features, demonstrating their potential for anonymization and dataset augmentation, and introduces a novel triplet loss to enhance identity disentanglement.

Contribution

It provides a comprehensive assessment of GANs' capacity to generate new identities and proposes a new triplet loss to improve identity disentanglement.

Findings

GANs can generate new, unique identities.

GANs are effective for anonymization and dataset augmentation.

The proposed triplet loss improves identity disentanglement.

Abstract

Generative Adversarial Networks (GANs) are now capable of producing synthetic face images of exceptionally high visual quality. In parallel to the development of GANs themselves, efforts have been made to develop metrics to objectively assess the characteristics of the synthetic images, mainly focusing on visual quality and the variety of images. Little work has been done, however, to assess overfitting of GANs and their ability to generate new identities. In this paper we apply a state of the art biometric network to various datasets of synthetic images and perform a thorough assessment of their identity-related characteristics. We conclude that GANs can indeed be used to generate new, imagined identities meaning that applications such as anonymisation of image sets and augmentation of training datasets with distractor images are viable applications. We also assess the ability of GANs to disentangle identity from other image characteristics and propose a novel GAN triplet loss that we show to improve this disentanglement.