AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Thermal-Det: Language-Guided Cross-Modal Distillation for Open-Vocabulary Thermal Object Detection

Yasiru Ranasinghe, Elim Schenck, Florence Yellin, Shuowen Hu, Christopher Funk, Vishal M. Patel

CVPR 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary object detection · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add scene-level caption loss (ablation)Thermal-Det · FLIR-AlignedAP: +0.012Improved
add scene-level caption loss (ablation)Thermal-Det · CAMELAP: +0.006Improved
add object-level caption loss (ablation)Thermal-Det · FLIR-AlignedAP: +0.028Improved
add object-level caption loss (ablation)Thermal-Det · CAMELAP: +0.020Improved
add RGB-to-thermal cross-modal distillation (L_KD) (ablation)Thermal-Det · FLIR-AlignedAP: +0.021Improved
add RGB-to-thermal cross-modal distillation (L_KD) (ablation)Thermal-Det · CAMELAP: +0.012Improved
add TTAH loss (ablation)Thermal-Det · FLIR-AlignedAP: 0.008 AP / 0.019 AP50 / 0.006 AP75Improved
use confidence-gated subclass selection instead of average pooling (ablation)TTAH · FLIR-AlignedAP: 0.234 -> 0.261Improved
use confidence-gated subclass selection instead of random (ablation)TTAH · FLIR-AlignedAP: 0.248 -> 0.261Improved
use confidence-gated subclass selection instead of average pooling (ablation)TTAH · CAMELAP: 0.559 -> 0.585Improved
apply thermal adaptation and distillation to MM-GDINOThermal-Det · FLIR-AlignedAP: 0.170 -> 0.234Improved
apply thermal adaptation and distillation to LLMDetThermal-Det · CAMELAP: 0.552 -> 0.574Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy