Research map / Detection and segmentation / Open-set and few-shot detection
CGSA: Class-Guided Slot-Aware Adaptation for Source-Free Object Detections
Boyang Dai, Zeng Fan, Zihao Qi, Meng Lou, Yizhou Yu
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 |
|---|---|---|---|
| add slot-aware adaptation (HSA + CGSC) to teacher-student SF-DAOD | RT-DETR · Cityscapes -> BDD100K | mAP@50: 38.3 -> 53.0 (vs TITAN) | Improved |
| add slot-aware adaptation | RT-DETR · Cityscapes -> Foggy-Cityscapes | mAP@50: 52.2 -> 53.2 (vs TITAN) | Improved |
| add slot-aware adaptation | RT-DETR · Sim10K -> Cityscapes | AP@50: 59.8 -> 67.7 (vs TITAN) | Improved |
| add slot-aware adaptation | RT-DETR · KITTI -> Cityscapes | AP@50: 53.2 -> 60.8 (vs TITAN) | Improved |
| add Hierarchical Slot Awareness (HSA) module (ablation) | CGSA · four cross-domain benchmarks | mAP | Improved |
| add Class-Guided Slot Contrast (CGSC) on top of HSA (ablation) | CGSA · four cross-domain benchmarks | mAP | Improved |
| increase slot number per level from 2 to 5 (depth 2) (ablation) | HSA · Cityscapes -> Foggy-Cityscapes | mAP: 50.9 -> 53.2 | Improved |
| increase slot number per level from 5 to 10 (depth 2) (ablation) | HSA · Cityscapes -> Foggy-Cityscapes | mAP: 53.2 -> 51.2 | Hurt |
| increase hierarchy depth from 2 to 3 (ablation) | HSA · Cityscapes -> Foggy-Cityscapes | mAP: 53.2 -> 50.3 (3 slots), 48.7 (4 slots) | Hurt |
Closest papers by meaning
- Simplifying Source-Free Domain Adaptation for Object Detection: Effective Self-Training Strategies and Performance Insights (ECCV 2024 · similarity 0.90)
- Enhancing Source-Free Domain Adaptive Object Detection with Low-confidence Pseudo Label Distillation (ECCV 2024 · similarity 0.89)
- DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection (NeurIPS 2024 · similarity 0.89)
- SEEN-DA: SEmantic ENtropy guided Domain-aware Attention for Domain Adaptive Object Detection (CVPR 2025 · similarity 0.88)
- Adaptive Slot Attention: Object Discovery with Dynamic Slot Number (CVPR 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.
