Age-Oriented Face Synthesis with Conditional Discriminator Pool and Adversarial Triplet Loss

TL;DR

This paper introduces a novel age-oriented face synthesis method that uses a Conditional Discriminator Pool and Adversarial Triplet Loss to improve synthesis accuracy and identity preservation, outperforming existing techniques.

Contribution

The paper proposes a new approach combining a Conditional Discriminator Pool and Adversarial Triplet Loss to enhance face aging synthesis accuracy and identity retention.

Findings

Outperforms state-of-the-art methods in synthesis accuracy.

Achieves stronger identity permanence in generated faces.

Effectively reduces intra-class variances in feature space.

Abstract

The vanilla Generative Adversarial Networks (GAN) are commonly used to generate realistic images depicting aged and rejuvenated faces. However, the performance of such vanilla GANs in the age-oriented face synthesis task is often compromised by the mode collapse issue, which may result in the generation of faces with minimal variations and a poor synthesis accuracy. In addition, recent age-oriented face synthesis methods use the L1 or L2 constraint to preserve the identity information on synthesized faces, which implicitly limits the identity permanence capabilities when these constraints are associated with a trivial weighting factor. In this paper, we propose a method for the age-oriented face synthesis task that achieves a high synthesis accuracy with strong identity permanence capabilities. Specifically, to achieve a high synthesis accuracy, our method tackles the mode collapse issue with a novel Conditional Discriminator Pool (CDP), which consists of multiple discriminators, each targeting one particular age category. To achieve strong identity permanence capabilities, our method uses a novel Adversarial Triplet loss. This loss, which is based on the Triplet loss, adds a ranking operation to further pull the positive embedding towards the anchor embedding resulting in significantly reduced intra-class variances in the feature space. Through extensive experiments, we show that our proposed method outperforms state-of-the-art methods in terms of synthesis accuracy and identity permanence capabilities, qualitatively and quantitatively.