Self-adversarial Multi-scale Contrastive Learning for Semantic Segmentation of Thermal Facial Images

Jitesh Joshi, N Bianchi-Berthouze, Youngjun Cho
in Working/Discussion Paper


Reliable segmentation of thermal facial images in unconstrained settings such
as thermal ambience and occlusions is challenging as facial features lack
salience. Limited availability of datasets from such settings further makes it
difficult to train segmentation networks. To address the challenge, we propose
Self-Adversarial Multi-scale Contrastive Learning (SAM-CL) as a generic
learning framework to train segmentation networks. SAM-CL framework constitutes
SAM-CL loss function and a thermal image augmentation (TiAug) as a
domain-specific augmentation technique to simulate unconstrained settings based
upon existing datasets collected from controlled settings. We use the
Thermal-Face-Database to demonstrate effectiveness of our approach. Experiments
conducted on the existing segmentation networks- UNET, Attention-UNET,
DeepLabV3 and HRNetv2 evidence the consistent performance gain from the SAM-CL
framework. Further, we present a qualitative analysis with UBComfort and
DeepBreath datasets to discuss how our proposed methods perform in handling
unconstrained situations.