Research map / Detection and segmentation / Open-set and few-shot detection
Domain Generalised Faster R-CNN
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 the complete DGFR-CNN regularisation to Faster R-CNN | Faster R-CNN · Foggy Cityscapes | mAP: 26.9 -> 38.90 | Helped |
| Add the complete DGFR-CNN regularisation to Faster R-CNN | Faster R-CNN · Rainy Cityscapes | mAP: 40.47 -> 44.66 | Helped |
| Add the complete DGFR-CNN regularisation | Faster R-CNN · GWHD OOD test | WADA: 53.73 -> 54.92 | Helped |
| Add the complete DGFR-CNN regularisation | Faster R-CNN · Sim10K + Cityscapes → BDD100K | mAP: 50.52 -> 52.02 | Helped |
| Add the complete DGFR-CNN regularisation | Faster R-CNN · Sim10K + BDD100K → Cityscapes | mAP: 71.43 -> 71.78 | Helped |
| Add the complete DGFR-CNN regularisation | Faster R-CNN · BDD100K + Cityscapes → Sim10K | mAP: 61.84 -> 62.50 | Helped |
| Add bounding-box alignment only (ablation) | Faster R-CNN · GWHD OOD test | WADA: 53.73 -> 54.48 | Helped |
| Add bounding-box alignment only (ablation) | Faster R-CNN · Sim10K + Cityscapes → BDD100K | mAP: 50.52 -> 35.76 | Hurt |
| Add bounding-box alignment only (ablation) | Faster R-CNN · Sim10K + BDD100K → Cityscapes | mAP: 71.43 -> 70.02 | Hurt |
| Add bounding-box alignment only (ablation) | Faster R-CNN · BDD100K + Cityscapes → Sim10K | mAP: 61.84 -> 54.30 | Hurt |
| Add class-conditional alignment only (ablation) | Faster R-CNN · GWHD OOD test | WADA: 53.73 -> 53.65 | No clear effect |
| Add class-conditional alignment only (ablation) | Faster R-CNN · Sim10K + Cityscapes → BDD100K | mAP: 50.52 -> 38.07 | Hurt |
Closest papers by meaning
- 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)
- Object-Aware Domain Generalization for Object Detection (AAAI 2024 · similarity 0.89)
- Towards Single-Source Domain Generalized Object Detection via Causal Visual Prompts (NeurIPS 2025 · similarity 0.89)
- Benchmarking Object Detectors under Real-World Distribution Shifts in Satellite Imagery (CVPR 2025 · similarity 0.89)
- G-NAS: Generalizable Neural Architecture Search for Single Domain Generalization Object Detection (AAAI 2024 · similarity 0.88)
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.