Research map / Label-efficient and robust learning / Domain adaptation and generalization
Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation
Yu-Jhe Li, Ci-Siang Lin, Yan-Bo Lin, Yu-Chiang Frank Wang
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 reconstruction loss L_rec (ablation) | PDA-Net · Market-1501 (source DukeMTMC-reID) | Rank-1 accuracy (%): 52.3 -> 75.2 | Improved |
| add reconstruction loss L_rec (ablation) | PDA-Net · DukeMTMC-reID (source Market-1501) | Rank-1 accuracy (%): 42.5 -> 63.2 | Improved |
| add pose loss L_pose (ablation) | PDA-Net · Market-1501 (source DukeMTMC-reID) | Rank-1 accuracy (%): 55.1 -> 75.2 | Improved |
| add pose loss L_pose (ablation) | PDA-Net · DukeMTMC-reID (source Market-1501) | Rank-1 accuracy (%): 45.5 -> 63.2 | Improved |
| use one shared pose discriminator instead of separate source and target ones (ablation) | PDA-Net · Market-1501 (source DukeMTMC-reID) | Rank-1 accuracy (%): 59.4 -> 75.2 | Improved |
| use one shared pose discriminator instead of separate source and target ones (ablation) | PDA-Net · DukeMTMC-reID (source Market-1501) | Rank-1 accuracy (%): 50.9 -> 63.2 | Improved |
| add domain loss L_domain (ablation) | PDA-Net · Market-1501 (source DukeMTMC-reID) | Rank-1 accuracy (%): 65.3 -> 75.2 | Improved |
| add domain loss L_domain (ablation) | PDA-Net · DukeMTMC-reID (source Market-1501) | Rank-1 accuracy (%): 56.5 -> 63.2 | Improved |
| add MMD loss to full PDA-Net (ablation) | PDA-Net · Market-1501 (source DukeMTMC-reID) | Rank-1 accuracy (%): 71.2 -> 75.2 | Improved |
| add MMD loss to full PDA-Net (ablation) | PDA-Net · DukeMTMC-reID (source Market-1501) | mAP (%): 35.8 -> 45.1 | Improved |
| add MMD loss to ResNet-50 baseline (ablation) | PDA-Net · Market-1501 (source DukeMTMC-reID) | Rank-1 accuracy (%): 44.2 -> 50.4 | Improved |
| add pose disentanglement and generation components to MMD baseline (ablation) | PDA-Net · Market-1501 (source DukeMTMC-reID) | Rank-1 accuracy (%): 50.4 -> 75.2 | Improved |
Closest papers by meaning
- Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification (ECCV 2020 · similarity 0.93)
- Learning to Adapt Across Dual Discrepancy for Cross-Domain Person Re-Identification (TPAMI 2022 · similarity 0.92)
- Unsupervised Cross-Dataset Transfer Learning for Person Re-Identification (CVPR 2016 · similarity 0.91)
- A Novel Unsupervised Camera-Aware Domain Adaptation Framework for Person Re-Identification (ICCV 2019 · similarity 0.91)
- Image-Image Domain Adaptation With Preserved Self-Similarity and Domain-Dissimilarity for Person Re-Identification (CVPR 2018 · similarity 0.90)
- Unsupervised Domain Adaptation for Person Re-identification via Heterogeneous Graph Alignment (AAAI 2021 · 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.
