PG-FM 提出按损坏类型自适应调制 RGB-T 目标检测特征
Shifting Focus by Reliability: Geometric Fusion Modulation for Robust RGB-T Detection
一篇 RGB-T 检测论文：不修复坏输入，而是让检测器按损坏类型自适应调特征，FLIR 上 mAP50 最多涨 20.8 点。
RGB-T 目标检测在可见光或热成像信号受损时精度会明显下降，而基于修复的方法延迟高且不一定提升下游精度。论文提出 PG-FM（Prompt-Guided Feature Modulation），根据每个模态估计出的损坏类型和严重程度对检测器特征做调制。在受控 RGB-T 损坏仿真中，PG-FM 保持干净数据性能，mAP50 在 FLIR 上最多提升 20.8 点，在 KAIST 上提升 19.9 点。模型无需重训练即可迁移到未修改的自然采集外部 RGB-T 数据集。
Shifting Focus by Reliability: Geometric Fusion Modulation for Robust RGB-T Detection
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.