Research map / Detection and segmentation / Open-set and few-shot detection
CSDA: Learning Category-Scale Joint Feature for Domain Adaptive Object Detection
Changlong Gao, Chengxu Liu, Yujie Dun, Xueming Qian
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 SGFF with scale discriminators to baseline (ablation) | CSDA (FCOS) · Cityscapes to Foggy Cityscapes | mAP: 38.9 -> 44.6 | Improved |
| use scale discriminator instead of scale classifier in SGFF (ablation) | CSDA (FCOS) · Cityscapes to Foggy Cityscapes | mAP: 43.5 -> 44.6 | Improved |
| add SAFE on top of SGFF (ablation) | CSDA (FCOS) · Cityscapes to Foggy Cityscapes | mAP: 44.6 -> 45.8 | Improved |
| add SAFE alone to baseline (ablation) | FCOS baseline · Cityscapes to Foggy Cityscapes | mAP: 38.9 -> 41.4 | Improved |
| add scale-guided constraint to graph-based feature fusion (ablation) | SGFF · Cityscapes to Foggy Cityscapes | mAP: +2.3 | Improved |
| set beta of scale mapping to 20 versus 5 or 40 (ablation) | CSDA (FCOS) · Cityscapes to Foggy Cityscapes | mAP: 44.1 -> 45.8 -> 44.6 | Mixed |
| apply CSDA scale-joint alignment versus best prior | Faster-RCNN · Sim10k to Cityscapes | mAP (car): 53.4 -> 56.9 | Improved |
| apply CSDA versus MGADA | Faster-RCNN · Cityscapes to Foggy Cityscapes | mAP: 44.3 -> 45.0 | Improved |
Closest papers by meaning
- Universal Domain Adaptive Object Detection via Dual Probabilistic Alignment (AAAI 2025 · similarity 0.92)
- Differential Alignment for Domain Adaptive Object Detection (AAAI 2025 · similarity 0.91)
- DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection (NeurIPS 2024 · similarity 0.90)
- SEEN-DA: SEmantic ENtropy guided Domain-aware Attention for Domain Adaptive Object Detection (CVPR 2025 · similarity 0.88)
- Large Self-Supervised Models Bridge the Gap in Domain Adaptive Object Detection (CVPR 2025 · similarity 0.88)
- Triple Feature Disentanglement for One-Stage Adaptive Object Detection (AAAI 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.
