Research map / Label-efficient and robust learning / Domain adaptation and generalization
Scale-Aware Domain Harmonization for Domain Adaptation Person Search
Huibing Wang, Guojian Zhao, Jinjia Peng, Linfeng Qi, Mingze Yao, Jiqing Zhang
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 SIA, SCR and BCR to DSCA baseline (ablation) | SCALE · PRW | mAP: 39.9 -> 41.7 | Improved |
| add SIA, SCR and BCR to DSCA baseline (ablation) | SCALE · CUHK-SYSU | mAP: 80.2 -> 82.3 | Improved |
| add SIA module (ablation) | SCALE · PRW | mAP: 41.1 -> 41.7 | Improved |
| use 2 sub-clusters instead of 1 in BCR split (ablation) | BCR · CUHK-SYSU | mAP: 80.4 -> 81.2 | Improved |
| use 3 sub-clusters instead of 2 in BCR split (ablation) | BCR · CUHK-SYSU | mAP: 81.2 -> 79.8 | Hurt |
| add both split and merge branches in BCR (ablation) | SCALE · PRW | mAP: 39.9 -> 40.8 | Improved |
| replace SDH with FPN-style modification (ablation) | SCALE · CUHK-SYSU | mAP: 82.3 -> 81.1 | Hurt |
| replace SDH with multi-scale training/testing (ablation) | SCALE · CUHK-SYSU | mAP: 82.3 -> 80.6 | Hurt |
| use both spatial and semantic paths instead of double spatial (ablation) | SDH · CUHK-SYSU | mAP: 81.0 -> 82.3 | Improved |
| evaluate on scale-mismatched subset (area < 10k) | SCALE vs baseline · PRW-style scale-mismatched subset | mAP: 53.53 -> 57.49 | Improved |
| add SDH module | SCALE · computational cost | parameters / GMac: 56.19M -> 58.64M; 414.09 -> 459.90 GMac | Hurt |
Closest papers by meaning
- Instance-Guided Scene Adaptation for Unsupervised Person Search (AAAI 2026 · similarity 0.90)
- Unsupervised Domain Adaptive Person Search via Dual Self-Calibration (AAAI 2025 · similarity 0.90)
- Gradient Harmonization in Unsupervised Domain Adaptation (TPAMI 2024 · similarity 0.87)
- Can We Evaluate Domain Adaptation Models Without Target-Domain Labels? (ICLR 2024 · similarity 0.86)
- Link-based Contrastive Learning for One-Shot Unsupervised Domain Adaptation (CVPR 2025 · similarity 0.86)
- CASUAL: Conditional Support Alignment for Domain Adaptation with Label Shift (AAAI 2025 · 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.
