Mutual Information Maximization on Disentangled Representations for Differential Morph Detection

TL;DR

This paper introduces a differential morph detection framework that leverages landmark and appearance disentanglement in face images, achieving state-of-the-art performance by analyzing distances in multiple domains.

Contribution

The novel framework combines landmark and appearance disentanglement with contrastive training to improve differential morph detection accuracy.

Findings

Achieves state-of-the-art detection performance

Effective across multiple morph datasets

Utilizes distances in landmark, appearance, and ID domains

Abstract

In this paper, we present a novel differential morph detection framework, utilizing landmark and appearance disentanglement. In our framework, the face image is represented in the embedding domain using two disentangled but complementary representations. The network is trained by triplets of face images, in which the intermediate image inherits the landmarks from one image and the appearance from the other image. This initially trained network is further trained for each dataset using contrastive representations. We demonstrate that, by employing appearance and landmark disentanglement, the proposed framework can provide state-of-the-art differential morph detection performance. This functionality is achieved by the using distances in landmark, appearance, and ID domains. The performance of the proposed framework is evaluated using three morph datasets generated with different methodologies.