Research map / Label-efficient and robust learning / Domain adaptation and generalization
Source-Free Object Detection by Learning To Overlook Domain Style
Check 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 |
|---|---|---|---|
| Adapt the source detector with style enhancement and graph alignments | Faster R-CNN · Pascal→Clipart | mAP: 44.1 -> 45.2 | Helped |
| Adapt the source detector with style enhancement and graph alignments | Faster R-CNN · Pascal→Watercolor | mAP: 56.9 -> 58.2 | Helped |
| Adapt the source detector with style enhancement and graph alignments | Faster R-CNN · Cityscapes→Foggy-Cityscapes | mAP: 35.5 -> 35.8 | Helped |
| Adapt the source detector with style enhancement and graph alignments | Faster R-CNN · KITTI→Cityscapes | AP on car: 43.6 -> 43.9 | Helped |
| Add style enhancement instead of random image augmentation (ablation) | LODS with alignment modules · Pascal→Watercolor | mAP: 53.1 -> 58.2 | Helped |
| Add style enhancement instead of random image augmentation (ablation) | LODS with alignment modules · Pascal→Clipart | mAP: 33.2 -> 45.2 | Helped |
| Use style transfer instead of random image augmentation (ablation) | LODS with alignment modules · Pascal→Watercolor | mAP: 53.1 -> 55.4 | Helped |
| Use style transfer instead of random image augmentation (ablation) | LODS with alignment modules · Pascal→Clipart | mAP: 33.2 -> 39.8 | Helped |
| Add style enhancement rather than style transfer (ablation) | LODS with alignment modules · Pascal→Watercolor | mAP: 55.4 -> 58.2 | Helped |
| Add style enhancement rather than style transfer (ablation) | LODS with alignment modules · Pascal→Clipart | mAP: 39.8 -> 45.2 | Helped |
| Add GIA alongside GCIA (ablation) | LODS · Pascal→Watercolor | mAP: 56.6 -> 58.2 | Helped |
| Add GIA alongside GCIA (ablation) | LODS · Pascal→Clipart | mAP: 44.5 -> 45.2 | Helped |
Closest papers by meaning
- Non-exemplar Domain Incremental Object Detection via Learning Domain Bias (AAAI 2024 · similarity 0.87)
- Active Domain Adaptation with False Negative Prediction for Object Detection (CVPR 2024 · similarity 0.87)
- Mean Teacher DETR with Masked Feature Alignment: A Robust Domain Adaptive Detection Transformer Framework (AAAI 2024 · similarity 0.87)
- Style Evolving along Chain-of-Thought for Unknown-Domain Object Detection (CVPR 2025 · similarity 0.87)
- Large Self-Supervised Models Bridge the Gap in Domain Adaptive Object Detection (CVPR 2025 · similarity 0.87)
- CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detection (CVPR 2024 · similarity 0.87)
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.