AI Paper Atlas

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

AAAI 2022 · Detection and segmentation › CNN features · approach: Context for hard detection conditions · 595 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use image-adaptive DIP enhancement with end-to-end detection trainingYOLOv3 · VOC_Foggy_testmAP: 63.40 -> 72.03Improved
Use image-adaptive DIP enhancement with end-to-end detection trainingYOLOv3 · RTTSmAP: 30.80 -> 37.08Improved
Use image-adaptive DIP enhancement with end-to-end detection trainingYOLOv3 · VOC_Dark_testmAP: 52.28 -> 59.40Improved
Use image-adaptive DIP enhancement with end-to-end detection trainingYOLOv3 · ExDark_testmAP: 37.03 -> 40.37Improved
Add hybrid data training (ablation)YOLOv3 · VOC_Foggy_testmAP: 31.05 -> 63.40Improved
Add DIP filter preprocessing (ablation)YOLOv3 with hybrid data training · VOC_Foggy_test and RTTSmAPImproved
Make DIP filter parameters image-adaptive instead of fixed (ablation)YOLOv3 with DIP · VOC_norm_testmAPImproved
Use all three filter groups: Defog, Pixel-wise, and Sharpen (ablation)DIP · RTTSmAP: 34.95 -> 37.08Improved
Use all three filter groups: Defog, Pixel-wise, and Sharpen (ablation)DIP · VOC_Foggy_testmAP: 70.14 -> 72.03Improved
Use all three filter groups: Defog, Pixel-wise, and Sharpen (ablation)DIP · VOC_norm_testmAP: 71.47 -> 73.23Improved
Add image-adaptive processing (ablation)YOLOv3 with hybrid training and DIP · VOC_norm_testmAPImproved
Use IA-YOLO instead of YOLOv3 IYOLOv3 · VOC_norm_test (fog experiments)mAP: 70.10 -> 73.23Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy