Research map / Detection and segmentation / Open-set and few-shot detection
Domain Adaptive Faster R-CNN for Object Detection in the Wild
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 image-level adaptation (ablation) | Faster R-CNN · SIM 10k → Cityscapes val | car AP: 30.12 -> 33.03 | Helped |
| Add instance-level adaptation (ablation) | Faster R-CNN · SIM 10k → Cityscapes val | car AP: 30.12 -> 35.79 | Helped |
| Combine image- and instance-level adaptation (ablation) | Faster R-CNN · SIM 10k → Cityscapes val | car AP: 30.12 -> 37.86 | Helped |
| Add consistency regularization to image- and instance-level adaptation (ablation) | Faster R-CNN · SIM 10k → Cityscapes val | car AP: 37.86 -> 38.97 | Helped |
| Add image-level, instance-level, and consistency adaptation | Faster R-CNN · Foggy Cityscapes val | mAP: 18.8 -> 27.6 | Helped |
| Use image-level adaptation only (ablation) | Faster R-CNN · Foggy Cityscapes val | mAP: 18.8 -> 25.7 | Helped |
| Use instance-level adaptation only (ablation) | Faster R-CNN · Foggy Cityscapes val | mAP: 18.8 -> 26.3 | Helped |
| Add image-level, instance-level, and consistency adaptation | Faster R-CNN · KITTI → Cityscapes (car) | AP: 30.2 -> 38.5 | Helped |
| Add image-level, instance-level, and consistency adaptation | Faster R-CNN · Cityscapes → KITTI (car) | AP: 53.5 -> 64.1 | Helped |
| Add consistency regularization to image- and instance-level adaptation (ablation) | Domain Adaptive Faster R-CNN · KITTI → Cityscapes (RPN top 300) | mIoU: 28.5 -> 30.3 | Helped |
| Use image-level adaptation rather than instance-level adaptation alone (ablation) | Faster R-CNN · KITTI → Cityscapes, varying target image scale | AP robustness to scale change | Helped |
Closest papers by meaning
- Domain-Specific Suppression for Adaptive Object Detection (CVPR 2021 · similarity 0.93)
- Exploring Categorical Regularization for Domain Adaptive Object Detection (CVPR 2020 · similarity 0.92)
- Domain Generalised Faster R-CNN (AAAI 2023 · similarity 0.91)
- Unbiased Faster R-CNN for Single-source Domain Generalized Object Detection (CVPR 2024 · similarity 0.89)
- Towards Unsupervised Model Selection for Domain Adaptive Object Detection (NeurIPS 2024 · similarity 0.88)
- CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detection (CVPR 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.