Research map / Detection and segmentation / Open-set and few-shot detection
SCAN: Cross Domain Object Detection with Semantic Conditioned Adaptation
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 |
|---|---|---|---|
| use SCAN instead of MeGA-CDA | cross-domain object detection · Cityscapes→Foggy Cityscapes | mAP0.5: 41.8+23.0 -> 42.1+23.7 | Helped |
| use SCAN instead of EPM | cross-domain object detection · Sim10k→Cityscapes | mAP0.5: 49.0 -> 52.6 | Helped |
| use SCAN instead of RPNPA | cross-domain object detection · KITTI→Cityscapes | mAP0.5: 44.8 -> 45.8 | Helped |
| add classification-guided alignment (ablation) | the baseline detector on Cityscapes→Foggy Cityscapes · Cityscapes→Foggy Cityscapes | mAP0.5: 33.2 -> 35.6+2.4 | Helped |
| add unbiased semantics to CKA (ablation) | the baseline detector on Cityscapes→Foggy Cityscapes · Cityscapes→Foggy Cityscapes | mAP0.5: 35.6+2.4 -> 40.9+7.7 | Helped |
| add semantic modeling (ablation) | CKA+US on Cityscapes→Foggy Cityscapes · Cityscapes→Foggy Cityscapes | mAP0.5: 38.7+5.5 -> 40.9+7.7 | Helped |
| add semantic conditioned manifestation (ablation) | CKA+US on Cityscapes→Foggy Cityscapes · Cityscapes→Foggy Cityscapes | mAP0.5: 36.9+3.7 -> 40.9+7.7 | Helped |
| add the conditional graph (ablation) | CKA+US on Cityscapes→Foggy Cityscapes · Cityscapes→Foggy Cityscapes | mAP0.5: 40.9+7.7 -> 41.4+8.2 | Helped |
| use adaptive node sampling instead of handcrafted threshold (ablation) | CKA+US+CG on Cityscapes→Foggy Cityscapes · Cityscapes→Foggy Cityscapes | mAP0.5: 41.0+7.8 -> 41.4+8.2 | Helped |
| add graph-based semantic transfer (ablation) | CKA+US+CG on Cityscapes→Foggy Cityscapes · Cityscapes→Foggy Cityscapes | mAP0.5: 41.4+8.2 -> 42.1+8.9 | Helped |
| add node transfer (ablation) | graph-based semantic transfer on Cityscapes→Foggy Cityscapes · Cityscapes→Foggy Cityscapes | mAP0.5: 41.5+8.3 -> 42.1+8.9 | Helped |
| add edge transfer (ablation) | graph-based semantic transfer on Cityscapes→Foggy Cityscapes · Cityscapes→Foggy Cityscapes | mAP0.5: 41.9+8.7 -> 42.1+8.9 | Helped |
Closest papers by meaning
- Adapting Object Detectors via Selective Cross-Domain Alignment (CVPR 2019 · similarity 0.92)
- Universal Domain Adaptive Object Detection via Dual Probabilistic Alignment (AAAI 2025 · similarity 0.90)
- CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detection (CVPR 2024 · similarity 0.89)
- SEEN-DA: SEmantic ENtropy guided Domain-aware Attention for Domain Adaptive Object Detection (CVPR 2025 · similarity 0.89)
- Mean Teacher DETR with Masked Feature Alignment: A Robust Domain Adaptive Detection Transformer Framework (AAAI 2024 · similarity 0.89)
- DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection (NeurIPS 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.