# C2FXNet: Coarse-to-Fine Scene Expert for Unified Object Detection across Adverse Weather

arXiv: https://arxiv.org/abs/2609.25693 · HTML: https://mlsanity.com/paper/2609.25693/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts.
- Builds on 23 of its 44 references that are in the map.
- First posted on arXiv 22 Sep 2026.

## Placed in

- Mixture-of-experts / [Vision mixture-of-experts](https://mlsanity.com/moe/vision-mixture-of-experts/)

## Builds on (most cited first, 23 of 23)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [Dynamic Routing Between Capsules](https://mlsanity.com/paper/1710.09829/) (2017)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [Benchmarking Single Image Dehazing and Beyond](https://mlsanity.com/paper/1712.04143/) (2017)
- [YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information](https://mlsanity.com/paper/2402.13616/) (2024)
- [YOLOv12: Attention-Centric Real-Time Object Detectors](https://mlsanity.com/paper/2502.12524/) (2025)
- [Scaled-YOLOv4: Scaling Cross Stage Partial Network](https://mlsanity.com/paper/2011.08036/) (2020)
- [Getting to Know Low-light Images with The Exclusively Dark Dataset](https://mlsanity.com/paper/1805.11227/) (2018)
- [Multi-Task Dense Prediction via Mixture of Low-Rank Experts](https://mlsanity.com/paper/2403.17749/) (2024)
- [Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization](https://mlsanity.com/paper/2402.12550/) (2024)
- [GDIP: Gated Differentiable Image Processing for Object-Detection in Adverse Conditions](https://mlsanity.com/paper/2209.14922/) (2022)
- [A Guide to Image and Video based Small Object Detection using Deep Learning : Case Study of Maritime Surveillance](https://mlsanity.com/paper/2207.12926/) (2022)
- [TogetherNet: Bridging Image Restoration and Object Detection Together via Dynamic Enhancement Learning](https://mlsanity.com/paper/2209.01373/) (2022)
- [ADAM-Dehaze: Adaptive Density-Aware Multi-Stage Dehazing for Improved Object Detection in Foggy Conditions](https://mlsanity.com/paper/2506.15837/) (2025)

## Abstract (arXiv)

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.