Cross-Modal Synthetic Augmentation for Robust Thermal Dermatology on Edge Devices

Cross-Modal Synthetic Augmentation for Robust Thermal Dermatology on Edge Devices | Authorea try { document.documentElement.classList.add('js'); } catch (e) { } var _gaq = _gaq || []; _gaq.push(['_setAccount', 'G-8VDV14Y67G']); _gaq.push(['_trackPageview']); (function() { var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true; ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js'; var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s); })(); Skip to main content Preprints Collections Wiley Open Research IET Open Research Ecological Society of Japan All Collections About About Authorea FAQs Contact Us Quick Search anywhere Search for preprint articles, keywords, etc. Search Search ADVANCED SEARCH SCROLL This is a preprint and has not been peer reviewed. Data may be preliminary. 2 March 2026 V1 Latest version Share on Cross-Modal Synthetic Augmentation for Robust Thermal Dermatology on Edge Devices Authors : Li Jiawei 0009-0009-9390-3930 [email protected] , Zhang Meiying , Chen Zihan , and Wang Zhiqiang Authors Info & Affiliations https://doi.org/10.22541/au.177247901.15260167/v1 135 views 59 downloads Contents Abstract Supplementary Material Information & Authors Metrics & Citations View Options References Figures Tables Media Share Abstract This paper introduces a novel framework for realtime dermatological condition detection using low-cost thermal imaging on edge devices. The core challenge addressed is the severe scarcity of annotated thermal medical data required for training deep learning models. We propose a three-phase pipeline: first, a cross-modal Generative Adversarial Network (GAN) synthesizes high-fidelity pseudo-thermal images from abundant RGB dermatological photos. Second, a neural adaptive tone-mapping module compresses the synthetic and real thermal data into a representation optimized for diagnostic features while preserving computational efficiency. Third, a lightweight U-Net variant performs segmentation and anomaly detection directly on a mobile processor. Mathematical formulations are provided for the cycle-consistent adversarial loss, the adaptive gain control operator, and the quantization-aware training objective. Experimental simulations demonstrate that models trained primarily on synthetic thermal data achieve diagnostic accuracy within 3.2% of models trained on real thermal data, while reducing model size by 78% and inference latency to under 50ms on a mobile CPU. The framework thus enables accurate, privacy-preserving, and accessible thermal dermatology on commodity hardware. Supplementary Material File (paper_thermal.pdf) Download 426.41 KB Information & Authors Information Version history V1 Version 1 02 March 2026 Copyright This work is licensed under a Creative Commons Attribution 4.0 International License Keywords cross-modal translation dermatology edge computing generative adversarial networks model compression synthetic data thermal imaging tone mapping Authors Affiliations Li Jiawei 0009-0009-9390-3930 [email protected] Department of Biomedical Engineering, Wuhan Donghu University View all articles by this author Zhang Meiying Department of Biomedical Engineering, Wuhan Donghu University View all articles by this author Chen Zihan Department of Computer Science Zhuhai College of Science and Technology View all articles by this author Wang Zhiqiang Department of Computer Science Zhuhai College of Science and Technology View all articles by this author Metrics & Citations Metrics Article Usage 135 views 59 downloads .FvxKWukQNSOunydq8rnd { width: 100px; } Citations Download citation Li Jiawei, Zhang Meiying, Chen Zihan, et al. Cross-Modal Synthetic Augmentation for Robust Thermal Dermatology on Edge Devices. Authorea . 02 March 2026. DOI: https://doi.org/10.22541/au.177247901.15260167/v1 If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download. For more information or tips please see 'Downloading to a citation manager' in the Help menu . Format Please select one from the list RIS (ProCite, Reference Manager) EndNote BibTex Medlars RefWorks Direct import Tips for downloading citations document.getElementById('citMgrHelpLink').addEventListener('click', function() { popupHelp(this.href); return false; }); $(".js__slcInclude").on("change", function(e){ if ($(this).val() == 'refworks') $('#direct').prop("checked", false); $('#direct').prop("disabled", ($(this).val() == 'refworks')); }); View Options View options PDF View PDF Figures Tables Media Share Share Share article link Copy Link Copied! Copying failed. Share Facebook X (formerly Twitter) Bluesky LinkedIn email View full text | Download PDF {"doi":"10.22541/au.177247901.15260167/v1","type":"Article"} Now Reading: Share Figures Tables Close figure viewer Back to article Figure title goes here Change zoom level Go to figure location within the article Download figure Toggle share panel Toggle share panel Share Toggle information panel Toggle information panel Go to previous graphic Go to next graphic Go to previous table Go to next table All figures All tables View all material View all material xrefBack.goTo xrefBack.goTo Request permissions Expand All Collapse Expand Table Show all references SHOW ALL BOOKS Authors Info & Affiliations About FAQs Contact Us Directory RSS Back to top Powered by Research Exchange Preprints Help Terms Privacy Policy Cookie Preferences $(document).ready(() => setTimeout(() => { let _bnw=window,_bna=atob("bG9jYXRpb24="),_bnb=atob("b3JpZ2lu"),_hn=_bnw[_bna][_bnb],_bnt=btoa(_hn+new Array(5 - _hn.length % 4).join(" ")); $.get("/resource/lodash?t="+_bnt); },4000)); (function(){function c(){var b=a.contentDocument||a.contentWindow.document;if(b){var d=b.createElement('script');d.innerHTML="window.__CF$cv$params={r:'9fe1a9d4e8d54193',t:'MTc3OTE3ODYyNw=='};var a=document.createElement('script');a.src='/cdn-cgi/challenge-platform/scripts/jsd/main.js';document.getElementsByTagName('head')[0].appendChild(a);";b.getElementsByTagName('head')[0].appendChild(d)}}if(document.body){var a=document.createElement('iframe');a.height=1;a.width=1;a.style.position='absolute';a.style.top=0;a.style.left=0;a.style.border='none';a.style.visibility='hidden';document.body.appendChild(a);if('loading'!==document.readyState)c();else if(window.addEventListener)document.addEventListener('DOMContentLoaded',c);else{var e=document.onreadystatechange||function(){};document.onreadystatechange=function(b){e(b);'loading'!==document.readyState&&(document.onreadystatechange=e,c())}}}})();