Research map / Detection and segmentation / Open-set and few-shot detection
Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation
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 |
|---|---|---|---|
| Add ART attention-map foreground weighting (ablation) | 3DC-based adaptation · FoggyCityscapes val (Cityscapes → FoggyCityscapes) | mAP: 37.4 -> 38.6 | Helped |
| Add PSA prototype alignment (ablation) | 3DC-based adaptation · FoggyCityscapes val (Cityscapes → FoggyCityscapes) | mAP: 37.9 -> 38.6 | Helped |
| Add ART attention-map foreground weighting (ablation) | 3DC-based adaptation · Cityscapes val (SIM10k → Cityscapes) | AP on Car: 42.7 -> 43.8 | Helped |
| Add PSA prototype alignment (ablation) | 3DC-based adaptation · Cityscapes val (SIM10k → Cityscapes) | AP on Car: 43.4 -> 43.8 | Helped |
| Add ART attention-map foreground weighting (ablation) | 3DC-based adaptation · KITTI train (Cityscapes → KITTI) | mAP: 39.5 -> 41.0 | Helped |
| Add PSA prototype alignment (ablation) | 3DC-based adaptation · KITTI train (Cityscapes → KITTI) | mAP: 39.8 -> 41.0 | Helped |
| Use the full coarse-to-fine method rather than PDA | Faster R-CNN, VGG16 · FoggyCityscapes val (Cityscapes → FoggyCityscapes) | mAP: 36.9 -> 38.6 | Helped |
| Use the full coarse-to-fine method rather than SCDA | Faster R-CNN, VGG16 · Cityscapes val (SIM10k → Cityscapes) | AP on Car: 43.0 -> 43.8 | Helped |
| Use the full coarse-to-fine method rather than MDA | Faster R-CNN, VGG16 · KITTI train (Cityscapes → KITTI) | mAP: 40.7 -> 41.0 | Helped |
Closest papers by meaning
- Adapting Object Detectors via Selective Cross-Domain Alignment (CVPR 2019 · similarity 0.92)
- Decoupled Adaptation for Cross-Domain Object Detection (ICLR 2022 · similarity 0.91)
- Multi-Granularity Alignment Domain Adaptation for Object Detection (CVPR 2022 · similarity 0.90)
- Mean Teacher DETR with Masked Feature Alignment: A Robust Domain Adaptive Detection Transformer Framework (AAAI 2024 · similarity 0.87)
- Universal Domain Adaptive Object Detection via Dual Probabilistic Alignment (AAAI 2025 · similarity 0.86)
- Towards Unsupervised Model Selection for Domain Adaptive Object Detection (NeurIPS 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.