Research map / Detection and segmentation / CNN features
Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions
Wenyu Liu, Gaofeng Ren, Runsheng Yu, Shi Guo, Jianke Zhu, Lei Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use image-adaptive DIP enhancement with end-to-end detection training | YOLOv3 · VOC_Foggy_test | mAP: 63.40 -> 72.03 | Improved |
| Use image-adaptive DIP enhancement with end-to-end detection training | YOLOv3 · RTTS | mAP: 30.80 -> 37.08 | Improved |
| Use image-adaptive DIP enhancement with end-to-end detection training | YOLOv3 · VOC_Dark_test | mAP: 52.28 -> 59.40 | Improved |
| Use image-adaptive DIP enhancement with end-to-end detection training | YOLOv3 · ExDark_test | mAP: 37.03 -> 40.37 | Improved |
| Add hybrid data training (ablation) | YOLOv3 · VOC_Foggy_test | mAP: 31.05 -> 63.40 | Improved |
| Add DIP filter preprocessing (ablation) | YOLOv3 with hybrid data training · VOC_Foggy_test and RTTS | mAP | Improved |
| Make DIP filter parameters image-adaptive instead of fixed (ablation) | YOLOv3 with DIP · VOC_norm_test | mAP | Improved |
| Use all three filter groups: Defog, Pixel-wise, and Sharpen (ablation) | DIP · RTTS | mAP: 34.95 -> 37.08 | Improved |
| Use all three filter groups: Defog, Pixel-wise, and Sharpen (ablation) | DIP · VOC_Foggy_test | mAP: 70.14 -> 72.03 | Improved |
| Use all three filter groups: Defog, Pixel-wise, and Sharpen (ablation) | DIP · VOC_norm_test | mAP: 71.47 -> 73.23 | Improved |
| Add image-adaptive processing (ablation) | YOLOv3 with hybrid training and DIP · VOC_norm_test | mAP | Improved |
| Use IA-YOLO instead of YOLOv3 I | YOLOv3 · VOC_norm_test (fog experiments) | mAP: 70.10 -> 73.23 | Improved |
Closest papers by meaning
- YOLOv10: Real-Time End-to-End Object Detection (NeurIPS 2024 · similarity 0.84)
- YOLO-RD: Introducing Relevant and Compact Explicit Knowledge to YOLO by Retriever-Dictionary (ICLR 2025 · similarity 0.84)
- Genuine Knowledge from Practice: Diffusion Test-Time Adaptation for Video Adverse Weather Removal (CVPR 2024 · similarity 0.83)
- YOLO-World: Real-Time Open-Vocabulary Object Detection (CVPR 2024 · similarity 0.83)
- Mamba YOLO: A Simple Baseline for Object Detection with State Space Model (AAAI 2025 · similarity 0.83)
- FBRT-YOLO: Faster and Better for Real-Time Aerial Image Detection (AAAI 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
