Explainable Thermal to Visible Face Recognition Using Latent-Guided Generative Adversarial Network
- Resource Type
- Conference
- Authors
- Anghelone, David; Chen, Cunjian; Faure, Philippe; Ross, Arun; Dantcheva, Antitza
- Source
- 2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021) Automatic Face and Gesture Recognition (FG 2021), 2021 16th IEEE International Conference on. :1-8 Dec, 2021
- Subject
- Computing and Processing
Visualization
Codes
Face recognition
Conferences
Gesture recognition
Generative adversarial networks
- Language
One of the main challenges in performing thermal-to-visible face image translation is preserving the identity across different spectral bands. Existing work does not effectively disentangle the identity from other confounding factors. In this paper, we propose a Latent-Guided Generative Adversarial Network (LG-GAN) to explicitly decompose an input image into identity code that is spectral-invariant and style code that is spectral-dependent. By using such a disentanglement, we are able to analyze the identity preservation by interpreting and visualizing the identity code. We present extensive face recognition experiments on two challenging Visible-Thermal face datasets. We show that the learned identity code is effective in preserving the identity, thus offering useful insights on interpreting and explaining thermal-to-visible face image translation.