The advantage of RGB-Thermal (RGB-T) detection lies in its ability to perform modality fusion and integrate cross-modality complementary information, enabling robust detection under diverse illumination and weather conditions. However, under extreme conditions where one modality exhibits poor quality and disturbs detection, modality separation is necessary to mitigate the impact of noise. To address this problem, we propose a Modality-Decoupled RGB-T detection framework with Query Fusion (MDQF) to balance modality complementation and separation. In this framework, DETR-like detectors are employed as separate branches for the RGB and TIR images, with query fusion interspersed between the two branches in each refinement stage. Herein, query fusion is performed by feeding the high-quality queries from one branch to the other one after query selection and adaptation. This design effectively excludes the degraded modality and corrects the predictions using high-quality queries. Moreover, the decoupled framework allows us to optimize each individual branch with unpaired RGB or TIR images, eliminating the need for paired RGB-T data. Extensive experiments demonstrate that our approach delivers superior performance to existing RGB-T detectors and achieves better modality independence.

翻译：RGB-热成像（RGB-T）检测的优势在于其能够进行模态融合并整合跨模态的互补信息，从而在多样化的光照与天气条件下实现鲁棒的检测。然而，在极端条件下，当某一模态质量较差并干扰检测时，需要进行模态分离以减轻噪声的影响。为解决这一问题，我们提出了一种基于查询融合的模态解耦RGB-T检测框架（MDQF），以平衡模态互补与分离。在该框架中，采用类DETR检测器作为RGB与热红外（TIR）图像的分支，并在每个精炼阶段通过查询融合将两个分支相互连接。具体而言，查询融合通过将经过查询选择与适配后的高质量查询从一个分支馈送至另一分支来实现。这一设计有效排除了退化模态的干扰，并利用高质量查询修正预测结果。此外，解耦框架允许我们使用非配对的RGB或TIR图像分别优化每个独立分支，从而无需配对的RGB-T数据。大量实验表明，我们的方法在性能上优于现有RGB-T检测器，并实现了更优的模态独立性。