English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Segmentation of thermal facial images is a challenging task. This is becausefacial features often lack salience due to high-dynamic thermal range scenesand occlusion issues. Limited availability of datasets from unconstrainedsettings further limits the use of the state-of-the-art segmentation networks,loss functions and learning strategies which have been built and validated forRGB images. To address the challenge, we propose Self-Adversarial Multi-scaleContrastive Learning (SAM-CL) framework as a new training strategy for thermalimage segmentation. SAM-CL framework consists of a SAM-CL loss function and athermal image augmentation (TiAug) module as a domain-specific augmentationtechnique. We use the Thermal-Face-Database to demonstrate effectiveness of ourapproach. Experiments conducted on the existing segmentation networks (UNET,Attention-UNET, DeepLabV3 and HRNetv2) evidence the consistent performancegains from the SAM-CL framework. Furthermore, we present a qualitative analysiswith UBComfort and DeepBreath datasets to discuss how our proposed methodsperform in handling unconstrained situations.

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