Research map / Label-efficient and robust learning / Domain adaptation and generalization
Learning Domain-Aware Detection Head with Prompt Tuning
Haochen Li, Rui Zhang, Hantao Yao, Xinkai Song, Yifan Hao, Yongwei Zhao, Ling Li, Yunji Chen
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 |
|---|---|---|---|
| learnable CoOp-style 16 domain-invariant tokens instead of hand-crafted prompt (ablation) | DA-Pro · Cityscapes->Foggy Cityscapes | AP: 28.5 -> 28.9 | Improved |
| add domain-related textual description dl_d (ablation) | DA-Pro · Cityscapes->Foggy Cityscapes | AP: 28.9 -> 29.2 | Improved |
| domain-specific tokens only (N=16) instead of domain-invariant (ablation) | DA-Pro · Cityscapes->Foggy Cityscapes | AP: 29.2 -> 28.9 | No clear effect |
| split 16 tokens into 8 domain-invariant and 8 domain-specific (ablation) | DA-Pro · Cityscapes->Foggy Cityscapes | AP: 29.2 -> 31.2 | Improved |
| add historical prompt ensemble (ablation) | DA-Pro · Cityscapes->Foggy Cityscapes | AP: 31.2 -> 31.9 | Improved |
| vary tokens per type M=N from 4 to 16 (with ensemble) (ablation) | DA-Pro · Cityscapes->Foggy Cityscapes | AP: 31.1 / 31.9 / 31.4 / 31.3 | Mixed |
| add loss terms progressively (L_s,t, L_s,st+L_t,st, L_ent) (ablation) | DA-Pro · Cityscapes->Foggy Cityscapes | mAP: 54.4 -> 55.5 | Improved |
| add L_t,{s} loss term (ablation) | DA-Pro · Cityscapes->Foggy Cityscapes | mAP: 55.5 -> 53.4 | Hurt |
| add historical prompt ensemble across loss forms (ablation) | DA-Pro · Cityscapes->Foggy Cityscapes | mAP: 55.5 -> 55.9 | Improved |
| replace hard pseudo labels with probability (soft) supervision (ablation) | DA-Pro · Cityscapes->Foggy Cityscapes | mAP: 55.9 -> 54.3 | Hurt |
| replace hard pseudo labels with probability (soft) supervision (ablation) | DA-Pro · SIM10K->Cityscapes | mAP: 62.9 -> 62.1 | Hurt |
| remove domain-related textual tokens dl_d (ablation) | DA-Pro · Cityscapes->Foggy Cityscapes | mAP: 55.9 -> 54.3 | Hurt |
Closest papers by meaning
- DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection (NeurIPS 2024 · similarity 0.95)
- SEEN-DA: SEmantic ENtropy guided Domain-aware Attention for Domain Adaptive Object Detection (CVPR 2025 · similarity 0.92)
- Universal Domain Adaptive Object Detection via Dual Probabilistic Alignment (AAAI 2025 · similarity 0.91)
- Large Self-Supervised Models Bridge the Gap in Domain Adaptive Object Detection (CVPR 2025 · similarity 0.90)
- Differential Alignment for Domain Adaptive Object Detection (AAAI 2025 · similarity 0.90)
- Non-exemplar Domain Incremental Object Detection via Learning Domain Bias (AAAI 2024 · similarity 0.90)
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.
