发表机构
Guilin University of Electronic Technology; Hainan University（桂林电子科技大学; 海南大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出C2FXNet，通过从粗到细的场景专家网络实现恶劣天气下的统一目标检测，在多个数据集上超越现有方法。
AI 中文摘要
恶劣天气下的目标检测仍然具有挑战性，因为严重的退化会削弱视觉质量并破坏不同场景中的语义特征表示。现有方法通常依赖于特定条件的设计，这限制了它们在统一检测器中的泛化能力。在本文中，我们提出了一种从粗到细的场景专家网络（C2FXNet），通过分层场景引导实现统一检测。具体来说，C2FXNet引入了一种双层级引导机制，包括一个多步推理路由器（MRR），它基于压缩的多尺度视觉线索和冻结的粗场景原型执行基于GRU的循环场景推理，以及一个精细场景细化（FSR）模块，该模块使用图像特定的语义线索来调制高层特征以处理局部变化。此外，一个场景感知的专家混合（SMoE）在MRR和FSR的联合引导下动态组合场景特定的专家。通过将粗场景推理与细粒度语义细化相结合，C2FXNet无需特定场景训练即可实现鲁棒的多场景检测。在RTTS、ExDark以及我们新构建的恶劣天气数据集（AWD）上进行的大量实验表明，C2FXNet在雾天、黑暗和晴朗条件下均持续优于最先进的方法，在RTTS、ExDark和AWD上分别达到63.70%、71.14%和54.19%的mAP。源代码将在该https URL上发布。
英文摘要
Object detection in adverse weather remains challenging because severe degradations weaken visual quality and disrupt semantic feature representations across diverse scenes. Existing methods usually rely on condition-specific designs, which limits their ability to generalize within a unified detector. In this paper, we propose a Coarse-to-Fine Scene Expert Network (C2FXNet) that achieves unified detection through hierarchical scene guidance. Specifically, C2FXNet introduces a dual-level guidance mechanism consisting of a Multi-step Reasoning Router (MRR), which performs GRU-based recurrent scene reasoning over compressed multi-scale visual cues and frozen coarse scene prototypes, and a Fine Scene Refinement (FSR) module, which uses image-specific semantic cues to modulate high-level features for local variation handling. Furthermore, a Scene-aware Mixture-of-Experts (SMoE) dynamically combines scene-specific experts under the joint guidance of MRR and FSR. By coupling coarse scene reasoning with fine-grained semantic refinement, C2FXNet enables robust multi-scene detection without scene-specific training. Extensive experiments on RTTS, ExDark, and our newly constructed Adverse Weather Dataset (AWD) demonstrate that C2FXNet consistently outperforms state-of-the-art methods across foggy, dark, and clear conditions, reaching 63.70%, 71.14%, and 54.19% mAP on RTTS, ExDark, and AWD, respectively. The source code will be released at https://github.com/PolarisFTL/C2FXNet.
Comments10 pages, 8 figures. Accepted at ACM Multimedia (ACM MM 2026)
