Research map / Detection and segmentation / Open-set and few-shot detection
Domain-Invariant Disentangled Network for Generalizable Object Detection
Chuang Lin, Zehuan Yuan, Sicheng Zhao, Peize Sun, Changhu Wang, Jianfei Cai
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 image-level disentanglement to Faster R-CNN (versus source-combined) (ablation) | Faster R-CNN · Cityscapes target (DG) | mAP@0.5 (%): 45.3 -> 47.1 | Improved |
| add instance-level disentanglement to Faster R-CNN (ablation) | Faster R-CNN · Cityscapes target (DG) | mAP@0.5 (%): 45.3 -> 46.1 | Improved |
| add instance-level disentanglement on top of image-level (ablation) | DIDN · Cityscapes target (DG) | mAP@0.5 (%): 47.1 -> 47.3 | Improved |
| add cross-level reconstruction on top of two-level disentanglement (ablation) | DIDN · Cityscapes target (DG) | mAP@0.5 (%): 47.3 -> 47.9 | Improved |
| add image-level disentanglement (ablation) | Faster R-CNN · Foggy Cityscapes target (DG) | mAP@0.5 (%): 31.3 -> 32.1 | Improved |
| add instance-level disentanglement (ablation) | Faster R-CNN · Foggy Cityscapes target (DG) | mAP@0.5 (%): 31.3 -> 31.9 | Mixed |
| add cross-level reconstruction on top of two-level disentanglement (ablation) | DIDN · Foggy Cityscapes target (DG) | mAP@0.5 (%): 33.2 -> 33.4 | Improved |
| add instance-level disentanglement on top of image-level (ablation) | DIDN · Foggy Cityscapes target (DG) | mAP@0.5 (%): 32.1 -> 33.2 | Improved |
| add cross-level reconstruction on top of two-level disentanglement (ablation) | DIDN · BDD100k target (DG) | mAP@0.5 (%): 22.2 -> 22.7 | Improved |
| add instance-level disentanglement on top of image-level (ablation) | DIDN · BDD100k target (DG) | mAP@0.5 (%): 21.1 -> 22.2 | Improved |
| directly align all source domains with a domain classifier | Faster R-CNN · Foggy Cityscapes target (DG) | mAP@0.5 (%): 31.3 -> 27.4 | Hurt |
| directly align all source domains with a domain classifier | Faster R-CNN · BDD100k target (DG) | mAP@0.5 (%): 18.9 -> 19.1 | No clear effect |
Closest papers by meaning
- Triple Feature Disentanglement for One-Stage Adaptive Object Detection (AAAI 2024 · similarity 0.90)
- Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment (CVPR 2024 · similarity 0.89)
- Unbiased Faster R-CNN for Single-source Domain Generalized Object Detection (CVPR 2024 · similarity 0.89)
- G-NAS: Generalizable Neural Architecture Search for Single Domain Generalization Object Detection (AAAI 2024 · similarity 0.89)
- Towards Single-Source Domain Generalized Object Detection via Causal Visual Prompts (NeurIPS 2025 · similarity 0.88)
- Object-Aware Domain Generalization for 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.
