发表机构
Dalian Maritime University; The Hong Kong University of Science and Technology (Guangzhou); Hubei University of Economics（大连海事大学; 香港科技大学（广州）; 湖北经济学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
ReDiffNet通过可靠性条件化的差分表示网络，解决低光无人机RGB-红外定向车辆检测中模态可靠性变化和小目标挑战，在DroneVehicle和VEDAI上分别达到85.3%和73.9%的mAP50。
AI 中文摘要
基于无人机的低光RGB-红外定向小型车辆检测对于夜间交通监控、应急响应和城市巡检至关重要。光照变化、前灯眩光、局部阴影和热响应退化导致空间上变化的模态可靠性，而车辆较小的视觉范围进一步削弱了边界、方向线索和热响应。因此，基于局部模态可靠性选择可信观测，同时利用模态偏好模糊区域中的互补判别信息，是构建有效多模态表示的关键。基于这一见解，我们提出了ReDiffNet，一种可靠性条件化的差分表示网络，其中模态可靠性同时指导证据选择和互补恢复。具体而言，退化感知的可靠性学习估计相对空间可靠性，不确定性引导的差分恢复利用跨模态差异来恢复模糊区域中的互补线索，可靠性条件化的重建将保留和恢复的证据整合为统一表示。ReDiffNet在DroneVehicle和VEDAI上分别实现了85.3%和73.9%的mAP50，证明了其有效性。
英文摘要
Low-light UAV-based RGB-infrared oriented small-vehicle detection is important for nighttime traffic monitoring, emergency response, and urban inspection. Illumination variations, headlight glare, local shadows, and thermal-response degradation cause spatially varying modality reliability, while the small visual extent of vehicles further weakens boundaries, orientation cues, and thermal responses. Accordingly, selecting trustworthy observations based on local modality reliability while further exploiting complementary discriminative information in regions with ambiguous modality preference is key to constructing effective multimodal representations. Based on this insight, we propose ReDiffNet, a reliability-conditioned differential representation network in which modality reliability guides both evidence selection and complementary recovery. Specifically, degradation-aware reliability learning estimates relative spatial reliability, uncertainty-guided differential recovery exploits cross-modal differences to recover complementary cues in ambiguous regions, and reliability-conditioned reconstruction integrates retained and recovered evidence into a unified representation. ReDiffNet achieves 85.3% and 73.9% mAP50 on DroneVehicle and VEDAI, respectively, supporting its effectiveness.
Comments5 pages, 1 figure, 5 tables
