Research map / Detection and segmentation / Open-set and few-shot detection
A Robust Learning Approach to Domain Adaptive Object Detection
Mehran Khodabandeh, Arash Vahdat, Mani Ranjbar, William G. Macready
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 |
|---|---|---|---|
| retrain on noisy target-domain pseudo boxes with robust label correction | Faster R-CNN · SIM 10K to Cityscapes | AP: 31.08 -> 42.56 | Improved |
| robust noisy-label training instead of plain pseudo-labeling | Pseudo-labeling · SIM 10K to Cityscapes | AP: 39.05 -> 42.56 | Improved |
| add bounding box refinement (Box-R) (ablation) | Noisy Labeling · SIM 10K to Cityscapes | AP: 41.28 -> 41.83 | Improved |
| add false negative correction (FN-Cor) (ablation) | Noisy Labeling · SIM 10K to Cityscapes | AP: 41.83 -> 42.56 | Improved |
| add Box-R (ablation) | Noisy Labeling · Cityscapes to Foggy Cityscapes | mAP: 35.62 -> 36.06 | Improved |
| add FN-Cor (ablation) | Noisy Labeling · Cityscapes to Foggy Cityscapes | mAP: 36.06 -> 36.45 | Improved |
| robust noisy-label training vs Feature Learning | Faster R-CNN · Cityscapes to Foggy Cityscapes | mAP: 34.70 -> 36.45 | Improved |
| add Box-R (ablation) | Noisy Labeling · KITTI to Cityscapes | AP: 42.03 -> 42.39 | Improved |
| add FN-Cor (ablation) | Noisy Labeling · KITTI to Cityscapes | AP: 42.39 -> 42.98 | Improved |
| add Box-R (ablation) | Noisy Labeling · Cityscapes to KITTI | AP: 76.36 -> 76.93 | Improved |
| add FN-Cor (ablation) | Noisy Labeling · Cityscapes to KITTI | AP: 76.93 -> 77.61 | Improved |
| robust training vs Feature Learning | Faster R-CNN · Cityscapes to KITTI | AP: 73.76 -> 77.61 | Improved |
Closest papers by meaning
- A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data (AAAI 2021 · similarity 0.91)
- Domain-Specific Suppression for Adaptive Object Detection (CVPR 2021 · similarity 0.91)
- Unsupervised Domain Adaptation of Object Detectors: A Survey (TPAMI 2023 · similarity 0.91)
- Simplifying Source-Free Domain Adaptation for Object Detection: Effective Self-Training Strategies and Performance Insights (ECCV 2024 · similarity 0.91)
- Towards Robust Adaptive Object Detection Under Noisy Annotations (CVPR 2022 · similarity 0.90)
- CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detection (CVPR 2024 · similarity 0.90)
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.
