Research map / Detection and segmentation / Open-set and few-shot detection
Implicit Non-Causal Factors are Out via Dataset Splitting for Domain Generalization Object Detection
Zhilong Zhang, Lei Zhang, Qiang He, Shuyin Xia, Guoyin Wang, Fuxiang Huang
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 |
|---|---|---|---|
| replace domain-label DAL with GB-DAL (granular-ball dataset splitting) | DAL · Multi-source DGOD C&B->Foggy Cityscapes | mAP: 27.0 -> 34.8 | Improved |
| replace DAL with GB-DAL | DAL · Multi-source DGOD F&B->Cityscapes | mAP: 35.6 -> 42.3 | Improved |
| replace DAL with GB-DAL | DAL · Multi-source DGOD C&F->BDD100k | mAP: 25.1 -> 26.4 | Improved |
| use GB-DAL instead of augmentation-free DivAlign alignment | DivAlign w/o Div · Multi-source DGOD C&B->Foggy Cityscapes | mAP: 32.2 -> 34.8 | Improved |
| add local GB-DAL to vanilla Faster R-CNN (ablation) | Faster R-CNN · Multi-source DGOD C&B->Foggy Cityscapes | mAP: 31.5 -> 34.1 | Improved |
| add global GB-DAL on top of local GB-DAL (ablation) | Faster R-CNN + local GB-DAL · Multi-source DGOD C&B->Foggy Cityscapes | mAP: 34.1 -> 34.8 | Improved |
| add SNF (simulated non-causal factors) to vanilla Faster R-CNN (ablation) | Faster R-CNN · Multi-source DGOD C&B->Foggy Cityscapes | mAP: 31.5 -> 35.6 | Improved |
| add SNF to GB-DAL (ablation) | GB-DAL · Multi-source DGOD C&B->Foggy Cityscapes | mAP: 34.8 -> 39.1 | Improved |
| add SNF plug-in to NP | NP · Multi-source DGOD F&B->Cityscapes | mAP: 35.8 -> 41.4 | Improved |
| add SNF plug-in to DivAlign | DivAlign · Multi-source DGOD C&F->BDD100k | mAP: 28.1 -> 28.4 | No clear effect |
| use SNF dual mechanism (simulation plus augmentation) instead of simulation only (ablation) | GB-DAL · Multi-source DGOD C&B->Foggy Cityscapes | mAP: 37.6 -> 39.1 | Improved |
| use conventional image augmentation instead of SNF (ablation) | GB-DAL · Multi-source DGOD C&B->Foggy Cityscapes | mAP: 34.8 -> 35.2 | No clear effect |
Closest papers by meaning
- Unbiased Faster R-CNN for Single-source Domain Generalized Object Detection (CVPR 2024 · similarity 0.89)
- Towards Single-Source Domain Generalized Object Detection via Causal Visual Prompts (NeurIPS 2025 · similarity 0.88)
- G-NAS: Generalizable Neural Architecture Search for Single Domain Generalization Object Detection (AAAI 2024 · similarity 0.87)
- Generalized Diffusion Detector: Mining Robust Features from Diffusion Models for Domain-Generalized Detection (CVPR 2025 · similarity 0.86)
- Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment (CVPR 2024 · similarity 0.86)
- Object-Aware Domain Generalization for Object Detection (AAAI 2024 · 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.
