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

Tianle Fang; Zhenbing Liu; Chong Yin; Bolun Li; Haoxiang Lu

cs.CVSep 22, 2026

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

Authors: Tianle Fang, Zhenbing Liu, Chong Yin, Bolun Li, Haoxiang Lu

Organizations: School of Computer Science and Information Security Guilin University of Electronic Technology Guilin, Guangxi, China

Abstract

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.

Figures & tables

Figure 1. (a) Existing methods: Separate models for each scene. (b) Our C2FXNet: Single unified model via coarse-to-fine text guidance.

Figure 2. Overview of proposed C2FXNet. It consists of three key modules: the Multi-step Reasoning Router (MRR) compresses multi-scale visual cues and performs GRU-based recurrent scene reasoning under coarse text-guided prototypes to generate interpretable routing weights, the Fine Scene Refinement (FSR) refines visual features using fine-grained textual cues, and the Scene-aware Mixture-of-Experts (SMoE) dynamically fuses fog, dark, and clear experts under the joint guidance of MRR and FSR, enabling robust and scene-consistent detection. Among them, $\gamma$ and $\beta$ denote two learnable linear layers.

Figure 3. Feature-level interpretability of FSR in clear, dark, and foggy scenes. FSR refines noisy SMoE activations into more coherent, object-centric, and weather-consistent feature responses.

Figure 4. t-SNE visualization of feature embeddings. C2FXNet produces more compact and better-separated clusters than the baseline for fog, dark, and clear scenes.

Dataset	Scene	#Img	#Bounding Boxes / Class
Dataset	Scene	#Img	Pers.	Bic.	Car	Moto.	Bus
AWD (Train)	Fog/Dark/Clear	41,685	157,707	4,014	26,064	4,875	3,489
AWD (Test)	Fog/Dark/Clear	8,805	33,012	948	5,796	1,113	855
RTTS	Fog	4,322	7,950	534	18,415	862	1,838
ExDark	Dark	7,363	7,460	1,120	2,927	1,072	706

Table 1. Statistics of datasets used for training and evaluation.

Method	Dataset	Publication	Params $\downarrow$	FLOPs $\downarrow$	Bicycle	Bus	Car	Motorbike	Person	mAP (%) $\uparrow$
TogetherNet ( Wang et al., 2022 )	RTTS	CGF’22	15.7M	26.1G	49.50	27.06	70.86	46.69	81.66	55.15
IA-YOLO ( Liu et al., 2022 )		AAAI’22	58.9M	65.6G	39.06	17.87	41.29	30.63	58.76	37.52
GDIP-YOLO ( Kalwar et al., 2023 )		ICRA’23	68.0M	105.2G	45.89	11.58	49.50	32.96	71.98	42.38
YOLOv9s ( Wang et al., 2024b )		ECCV’24	7.1M	26.4G	40.73	23.41	61.13	33.17	79.76	47.64
YOLOv10s ( Wang et al., 2024a )		NeurIPS’24	7.6M	24.5G	42.22	23.65	60.42	33.60	78.72	47.72
YOLOv11s ( Jocher and Qiu, 2024 )		-	9.0M	21.5G	53.64	37.68	72.56	53.23	82.87	60.00

Table 2. Comparison of C2FXNet with previous detectors on RTTS, ExDark, and AWD datasets. C2FXNet attains optimal parameter efficiency while achieving the highest detection accuracy. The best and second-best results are boldfaced and underlined.

Figure 5. Visual comparison on the RTTS dataset under foggy conditions. C2FXNet detects more objects with clearer boundaries and higher confidence, especially for small or distant targets that other methods miss.

Figure 6. Visual comparison on the ExDark dataset under low-light conditions. C2FXNet achieves more accurate and confident detections, successfully identifying objects in dark and overexposed areas.

Figure 7. Visual comparison on the AWD dataset under dark, foggy, and clear conditions. C2FXNet maintains consistent detection quality and higher confidence across scenes, highlighting its strong cross-weather adaptability.

Method	Scene	Bicycle	Bus	Car	Motorbike	Person	mAP (%) $\uparrow$
Baseline	Fog	33.07	61.34	45.77	54.58	65.67	52.09
C2FXNet (Ours)	Fog	34.46	63.58	45.01	56.94	66.42	53.28
Baseline	Dark	30.48	62.62	44.61	49.38	63.11	50.04
C2FXNet (Ours)	Dark	31.66	63.91	44.13	53.17	63.61	51.30
Baseline	Clear	41.79	65.47	54.63	57.88	72.48	58.45
C2FXNet (Ours)	Clear	42.61	68.57	54.58	60.14	73.77	59.22

Table 3. Comparison of C2FXNet and the baseline on the AWD dataset under fog, dark, and clear scenes. C2FXNet yields consistent gains across most categories, highlighting the effectiveness of scene-aware adaptation.

Ablation	MRR	FSR	Text Encoder	SMoE	Aggregation	mAP (%) $\uparrow$
Ablation	MRR	FSR		SMoE	Aggregation	RTTS	ExDark	AWD
(a)	✗	✗	✗	✗	–	61.99	69.16	53.53
(b)	✓	✗	✗	$1\times$	–	58.91 ${}_{\text{{\color[rgb]{0,0.7,0}-3.08}}}$	69.74 ${}_{\text{{\color[rgb]{0.8,0,0}+0.58}}}$	48.61 ${}_{\text{{\color[rgb]{0,0.7,0}-4.92}}}$
(c)	✗	✓	✗	$1\times$	–	60.05 ${}_{\text{{\color[rgb]{0,0.7,0}-1.94}}}$	69.57 ${}_{\text{{\color[rgb]{0.8,0,0}+0.41}}}$	48.80 ${}_{\text{{\color[rgb]{0,0.7,0}-4.73}}}$
(d)	✓	✗	all-MiniLM-L6-v2	$1\times$	–	61.38 ${}_{\text{{\color[rgb]{0,0.7,0}-0.61}}}$	69.95 ${}_{\text{{\color[rgb]{0.8,0,0}+0.79}}}$	52.09 ${}_{\text{{\color[rgb]{0,0.7,0}-1.44}}}$
(e)	✓	✓	ViT-B-32	$1\times$	–	59.72 ${}_{\text{{\color[rgb]{0,0.7,0}-2.27}}}$	71.03 ${}_{\text{{\color[rgb]{0.8,0,0}+1.87}}}$	50.16 ${}_{\text{{\color[rgb]{0,0.7,0}-3.37}}}$

Table 4. Ablation for C2FXNet components on all-weather benchmarks. We adopt two frozen text encoders: all-MiniLM-L6-v2 and ViT-B-32 . “

n

× SMoE” denotes the number of expert groups, each containing three sub-experts corresponding to the above scenes, while multiple groups are fused by different aggregation strategies ( mean , sum , concat ). “✓” and “✗” denote with and without each component, respectively.

Figure 8. Visualization of detection results produced by C2FXNet on the VOC-Rain and VOC-Snow datasets.

Method	Dataset	Bicycle	Bus	Car	Motorbike	Person	mAP $(\%)\uparrow$
Baseline	Rain	40.94	67.57	50.11	46.72	65.26	54.12
C2FXNet (Ours)	Rain	37.65	74.96	48.82	46.40	68.22	55.21
Baseline	Snow	31.33	59.27	30.18	30.81	52.32	40.78
C2FXNet (Ours)	Snow	28.28	61.42	33.50	30.90	55.85	41.99

Table 5. Quantitative evaluation on VOC-Rain and VOC-Snow, comparing the baseline model with our C2FXNet across five object categories and the overall mAP.

Object Detection

Object detection locates and classifies objects in images or video, balancing localization accuracy, robustness, and inference speed.

See all 624 papers

FR-DETR: Frequency and Recurrent Feature Refinement for Robust Object Detection under Adverse Weather
Jun 29, 2026Tuan-Duc Nguyen, Duc-Trong LeFrequency-Domain Feature Learning Detection Transformer
FPT Software AI Center · VNU University of Engineering and Technology
AW-MoE: All-Weather Mixture of Experts for Robust Multi-Modal 3D Object Detection
Mar 17, 2026Hongwei Lin, Xun Huang, Chenglu Wen +13D Object Detection Autonomous Driving
Fujian Key Laboratory of Urban Intelligent Sensing and Computing and the School of Informatics, Xiamen University, Xiamen, FJ 361005, China · Zhongguancun Academy, Beijing, China
Detect in Any Scene: An Agentic Framework for Object Detection with Experience-Aware Reasoning
May 29, 2026Wenlun Zhang, Jun Yin, Kentaro YoshiokaObject Detection
Keio University · Tsinghua University

Jun 29, 2026J/K move · Enter open · S save

FR-DETR: Frequency and Recurrent Feature Refinement for Robust Object Detection under Adverse Weather

Tuan-Duc Nguyen, Duc-Trong Le

FPT Software AI Center · VNU University of Engineering and Technology

Frequency-Domain Feature Learning Detection Transformer Object Detection

Open paper AskPDF arXiv

Object detection under adverse weather remains challenging due to severe visual degradations and domain shifts. Existing enhancer-based approaches attempt to improve detection by cascading an enhancer with a detector, but they introduce redundant feature extraction and incur high computational cost with limited accuracy gains when paired with SOTA detectors. We propose FR-DETR, a detector-centric framework that refines features rather than images, focusing enhancement on regions of interest and leveraging frequency-domain cues. Specifically, we design (I) a Frequency Refinement Module that dynamically separates and reweights low- and high-frequency components to improve foreground-background discrimination, and (II) a Recurrent Focus Refinement Module (RFRM) that iteratively refines features using coarse predictions as guidance. Extensive experiments demonstrate that FR-DETR achieves superior detection accuracy under adverse weather while being significantly more computationally efficient than enhancer-based methods. Our implementation is available at https://github.com/ducnt1210/FR-DETR.

Abstract

Object Detection

Explore similar work

FR-DETR: Frequency and Recurrent Feature Refinement for Robust Object Detection under Adverse Weather

AW-MoE: All-Weather Mixture of Experts for Robust Multi-Modal 3D Object Detection

Detect in Any Scene: An Agentic Framework for Object Detection with Experience-Aware Reasoning