Research map / Detection and segmentation / Open-set and few-shot detection
Revisiting Domain-Adaptive Object Detection in Adverse Weather by the Generation and Composition of High-Quality Pseudo-Labels
Rui Zhao, Huibin Yan, Shuoyao Wang
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 |
|---|---|---|---|
| add global feature alignment (ablation) | YOLOv5L source-only detector · Cityscapes to RTTS | mAP: 46.5 -> 48.2 | Improved |
| add image-to-image translation (rendering and restoration) (ablation) | YOLOv5L with GFA · Cityscapes to RTTS | mAP: 48.2 -> 49.7 | Improved |
| replace CIoU with IAoU loss (ablation) | YOLOv5L with GFA and I2I · Cityscapes to RTTS | mAP: 49.7 -> 51.8 | Improved |
| add mean-teacher training (ablation) | YOLOv5L with GFA, I2I, IAoU · Cityscapes to RTTS | mAP: 51.8 -> 54.8 | Improved |
| add joint-filtering and student-aware pseudo-label filtering (PLF) (ablation) | Mean-teacher YOLOv5L · Cityscapes to RTTS | mAP: 54.8 -> 58.9 | Improved |
| full generation-composition framework vs source-only | YOLOv5L · Foggy Cityscapes | mAP: 46.5 -> 58.4 | Improved |
| full method vs best baseline SSDA-YOLO | YOLOv5L · Rain Cityscapes | mAP: 52.6 -> 57.5 | Improved |
| full method vs oracle on Foggy Cityscapes | YOLOv5L · Foggy Cityscapes | mAP: 58.4 vs 59.0 (oracle) | No clear effect |
Closest papers by meaning
- Large Self-Supervised Models Bridge the Gap in Domain Adaptive Object Detection (CVPR 2025 · similarity 0.87)
- Semantic Segmentation in Multiple Adverse Weather Conditions with Domain Knowledge Retention (AAAI 2024 · similarity 0.87)
- Parsing All Adverse Scenes: Severity-Aware Semantic Segmentation with Mask-Enhanced Cross-Domain Consistency (AAAI 2024 · similarity 0.87)
- CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detection (CVPR 2024 · similarity 0.86)
- Mean Teacher DETR with Masked Feature Alignment: A Robust Domain Adaptive Detection Transformer Framework (AAAI 2024 · similarity 0.86)
- Continuous Adverse Weather Removal via Degradation-Aware Distillation (CVPR 2025 · similarity 0.86)
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.
