Research map / Label-efficient and robust learning / Domain adaptation and generalization
Camera-Driven Representation Learning for Unsupervised Domain Adaptive Person Re-identification
Geon Lee, Sanghoon Lee, Dohyung Kim, Younghoon Shin, Yongsang Yoon, Bumsub Ham
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 camera-driven curriculum (CaCL) over cross-entropy+triplet loss (ablation) | UDA reID with ResNet-50 · Market1501-to-MSMT17 | mAP: 23.4 -> 31.1 | Improved |
| use random curriculum sequence instead of none (ablation) | CTL baseline · Market1501-to-MSMT17 | mAP: 23.4 -> 24.4 | Improved |
| replace random curriculum with MMD-based camera-driven scheduler (with CD loss) (ablation) | CaCL · Market1501-to-MSMT17 | mAP: 30.4 -> 36.5 | Improved |
| add camera-diversity loss on top of CaCL (ablation) | CaCL · Market1501-to-MSMT17 | mAP: 31.1 -> 36.5 | Improved |
| add camera-diversity loss without curriculum (ablation) | baseline CTL · MSMT17-to-Market1501 | mAP: 79.2 -> 81.8 | Improved |
| CD loss instead of UGID loss (ablation) | UDA reID · Market1501-to-MSMT17 | mAP: 32.3 -> 36.5 | Improved |
| combine CD loss with UGID weights (ablation) | CaCL with CD loss · Market1501-to-MSMT17 | mAP: 36.5 -> 38.4 | Improved |
| combine CD loss with UGID weights (ablation) | CaCL with CD loss · Unreal-to-MSMT17 | mAP: 40.3 -> 41.2 | Improved |
Closest papers by meaning
- A Novel Unsupervised Camera-Aware Domain Adaptation Framework for Person Re-Identification (ICCV 2019 · similarity 0.94)
- Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification (ICLR 2020 · similarity 0.93)
- Joint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-Identification (ECCV 2020 · similarity 0.92)
- Towards Discriminative Representation Learning for Unsupervised Person Re-Identification (ICCV 2021 · similarity 0.92)
- Domain Adaptive Attention Learning for Unsupervised Person Re-Identification (AAAI 2020 · similarity 0.92)
- Exploring the Camera Bias of Person Re-identification (ICLR 2025 · similarity 0.91)
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.
