Mutual Information Maximization on Disentangled Representations for Differential Morph Detection

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 1731-1741, 2020.

Cited by: 0|Views4

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 ...More

Code:

Data:

Full Text
Bibtex
Your rating :
0

 

Tags
Comments