Polarimetric Thermal to Visible Face Verification via Self-Attention Guided Synthesis

Abstract

Polarimetric thermal to visible face verification entails matching two images that contain significant domain differences. Several recent approaches have attempted to synthesize visible faces from thermal images for cross-modal matching. In this paper, we take a different approach in which rather than focusing only on synthesizing visible faces from thermal faces, we also propose to synthesize thermal faces from visible faces. Our intuition is based on the fact that thermal images also contain some discriminative information about the person for verification. Deep features from a pre-trained Convolutional Neural Network (CNN) are extracted from the original as well as the synthesized images. These features are then fused to generate a template which is then used for verification. The proposed synthesis network is based on the self-attention generative adversarial network (SAGAN) which essentially allows efficient attention-guided image synthesis. Extensive experiments on the ARL polarimetric thermal face dataset demonstrate that the proposed method achieves state-of-the-art performance.

arXiv commentThis work is accepted at the 12th IAPR International Conference On Biometrics (ICB 2019)

References in corpus (3)

• Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks
• Polarimetric Thermal to Visible Face Verification via Attribute Preserved Synthesis
• GP-GAN: Gender Preserving GAN for Synthesizing Faces from Landmarks

Cited by in corpus (7)

• Recent Advances in Deep Learning Techniques for Face Recognition
• Towards NIR-VIS Masked Face Recognition
• Multi-Scale Thermal to Visible Face Verification via Attribute Guided Synthesis
• Heterogeneous Face Frontalization via Domain Agnostic Learning
• Simultaneous Face Hallucination and Translation for Thermal to Visible Face Verification using Axial-GAN
• Multimodal Face Synthesis from Visual Attributes
• Multi-Attribute guided Thermal Face Image Translation based on Latent Diffusion Model