Research map / Detection and segmentation / Open-set and few-shot detection
RT-SDGOD: Real-Time Single-Domain Generalized Object Detection
Yupeng Zhang, Fangzhuo Gao, Ruize Han, Wei Feng, Liang Wan
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 one-to-many (O2M) supervision (ablation) | RF-DETR-L · SDGOD avg | mAP@50: 51.9 -> 52.5 | Improved |
| add Discriminative Evidence Diversity Learning (DEDL) (ablation) | RF-DETR-L+O2M · SDGOD avg | mAP@50: 52.5 -> 53.8 | Improved |
| add Dual-view Evidence Consistency Learning (DvECL) (ablation) | RF-DETR-L+O2M+DEDL · SDGOD avg | mAP@50: 53.8 -> 54.4 | Improved |
| apply RT-SDGDet vs baseline on severe domains | RF-DETR-L · Night-Rainy | mAP@50: 33.5 -> 39.0 | Improved |
| apply RT-SDGDet vs baseline on source domain | RF-DETR-L · Daytime-Clear | mAP@50: 68.6 -> 68.9 | No clear effect |
| add RT-SDGDet training | RF-DETR-L · SDGOD | false negative rate: 18.5 -> 15.7 | Improved |
| use RT-SDGDet vs domain augmentation (MAD/NP/PhysAug) | RF-DETR-L · SDGOD avg | mAP@50: 53.3 -> 54.4 | Improved |
| raise lambda_O2M beyond 0.5 (ablation) | RT-SDGDet · SDGOD avg | mAP@50: 52.5 -> 52.1 at 1.0 | Hurt |
| raise lambda_DEDL beyond 0.5 (ablation) | RT-SDGDet · SDGOD avg | mAP@50: 53.7 -> 52.8 at 1.0 | Hurt |
| raise lambda_DvECL beyond 0.3 (ablation) | RT-SDGDet · SDGOD avg | mAP@50: 54.4 -> 54.2 at 1.0 | Hurt |
| vary similarity margin m in [0,0.5] (ablation) | RT-SDGDet · SDGOD avg | mAP@50: 53.1-53.8 vs 52.5 (+O2M) | No clear effect |
Closest papers by meaning
- Towards Single-Source Domain Generalized Object Detection via Causal Visual Prompts (NeurIPS 2025 · similarity 0.90)
- Unbiased Faster R-CNN for Single-source Domain Generalized Object Detection (CVPR 2024 · similarity 0.90)
- Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment (CVPR 2024 · similarity 0.89)
- Benchmarking Object Detectors under Real-World Distribution Shifts in Satellite Imagery (CVPR 2025 · similarity 0.88)
- Generalized Diffusion Detector: Mining Robust Features from Diffusion Models for Domain-Generalized Detection (CVPR 2025 · similarity 0.88)
- G-NAS: Generalizable Neural Architecture Search for Single Domain Generalization Object Detection (AAAI 2024 · similarity 0.87)
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.
