---
title: "Shifting Focus by Reliability: Geometric Fusion Modulation for Robust RGB-T Detection"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2610.41204v1"
permalink: "https://feed.astralor.com/items/itm_ec89e4d5cab423f6ab2e43a3"
published: "2026-10-30T03:26:37.000Z"
score: 54
channel: "tech"
tags: ["推理效率","Shifting Focus","Reliability","Geometric Fusion Modulation","Robust RGB-T Detection","RGB-thermal","RGB-T","Restoration-based"]
---

# Shifting Focus by Reliability: Geometric Fusion Modulation for Robust RGB-T Detection

## At a glance

RGB-thermal (RGB-T) object detectors combine visible and thermal imagery for robust detection, but signal corruption in either stream can substantially degrade accuracy. Restoration-based methods incur significant laten…

## Key points

- RGB-thermal (RGB-T) object detectors combine visible and thermal imagery for robust detection, but signal corruption in either stream can substantially degrade accuracy.
- Restoration-based methods incur significant latency and do not consistently improve downstream accuracy, raising a more direct question: rather than restoring corrupted inputs, can we efficiently adapt the detector to t…
- Conventional PEFT offers an efficient route, but its input-independent corrections cannot track diverse test-time corruptions.

## Full text

RGB-thermal (RGB-T) object detectors combine visible and thermal imagery for robust detection, but signal corruption in either stream can substantially degrade accuracy. Restoration-based methods incur significant latency and do not consistently improve downstream accuracy, raising a more direct question: rather than restoring corrupted inputs, can we efficiently adapt the detector to their varying signal quality? Conventional PEFT offers an efficient route, but its input-independent corrections cannot track diverse test-time corruptions. Our controlled corruption sweeps show that corruption types have similar effects near clean conditions but diverge increasingly with severity, motivating corruption-aware, per-input adaptation. We therefore propose PG-FM (Prompt-Guided Feature Modulation), which adapts RGB-T object detectors to the estimated corruption type and severity of each modality. Under controlled RGB-T corruption simulations, PG-FM preserves clean-set performance, improves mAP50 by up to 20.8 points on FLIR and 19.9 points on KAIST, and transfers without retraining to unmodified, naturally acquired external RGB-T datasets.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_ec89e4d5cab423f6ab2e43a3