SemOD: Semantic Enabled Object Detection Network under Various Weather Conditions

2025/11/27 by Aiyinsi Zuo, Zuo, Aiyinsi, Zhaoliang Zheng +1
Computer Science · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image Enhancement Techniques #Multimodal Machine Learning Applications #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2511.22142

openalex publication_date 2025/11/27 · openalex created_date 2025/12/03 · openalex updated_date 2026/07/28

Abstract

In the field of autonomous driving, camera-based perception models are mostly trained on clear weather data. Models that focus on addressing specific weather challenges are unable to adapt to various weather changes and primarily prioritize their weather removal characteristics. Our study introduces a semantic-enabled network for object detection in diverse weather conditions. In our analysis, semantics information can enable the model to generate plausible content for missing areas, understand object boundaries, and preserve visual coherency and realism across both filled-in and existing portions of the image, which are conducive to image transformation and object recognition. Specific in implementation, our architecture consists of a Preprocessing Unit (PPU) and a Detection Unit (DTU), where the PPU utilizes a U-shaped net enriched by semantics to refine degraded images, and the DTU integrates this semantic information for object detection using a modified YOLO network. Our method pioneers the use of semantic data for all-weather transformations, resulting in an increase between 1.47% to 8.80% in mAP compared to existing methods across benchmark datasets of different weather. This highlights the potency of semantics in image enhancement and object detection, offering a comprehensive approach to improving object detection performance. Code will be available at https://github.com/EnisZuo/SemOD.

Citations

• YOLOv11: An Overview of the Key Architectural Enhancements
• Micrograph segmentations for DDEVD
• Efficient Computation Sharing for Multi-Task Visual Scene Understanding
• InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
• Domain Adaptive Object Detection for Autonomous Driving under Foggy Weather
• V2XP-ASG: Generating Adversarial Scenes for Vehicle-to-Everything Perception
• CF-YOLO: Cross Fusion YOLO for Object Detection in Adverse Weather with a High-quality Real Snow Dataset
• Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions
• TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions
• SwinIR: Image Restoration Using Swin Transformer
• Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection
• Image Inpainting Guided by Coherence Priors of Semantics and Textures
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• URIE: Universal Image Enhancement for Visual Recognition in the Wild
• Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation
• Deep High-Resolution Representation Learning for Visual Recognition
• Deep High-Resolution Representation Learning for Visual Recognition
• Heavy Rain Image Restoration: Integrating Physics Model and Conditional\n Adversarial Learning
• Effects of Image Degradations to CNN-based Image Classification
• Gated Fusion Network for Single Image Dehazing
• Densely Connected Pyramid Dehazing Network
• Domain Adaptive Faster R-CNN for Object Detection in the Wild
• Attentive Generative Adversarial Network for Raindrop Removal from a Single Image
• Squeeze-and-Excitation Networks
• Semantic Foggy Scene Understanding with Synthetic Data
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• Adherent Raindrop Modeling, Detection and Removal in Video
• U-Net: Convolutional Networks for Biomedical Image Segmentation
• Fast R-CNN
• Fully Convolutional Networks for Semantic Segmentation
• Microsoft COCO: Common Objects in Context

Related

• D-YOLO a robust framework for object detection in adverse weather conditions
• FogGuard: guarding YOLO against fog using perceptual loss
• Enhancing Autonomous Vehicle Perception in Adverse Weather through Image Augmentation during Semantic Segmentation Training
• FriendNet: Detection-Friendly Dehazing Network
• YOLO-Vehicle-Pro: A Cloud-Edge Collaborative Framework for Object Detection in Autonomous Driving under Adverse Weather Conditions