Research map / Label-efficient and robust learning / Semi-supervised learning
Dual Pseudo-Labels Interactive Self-Training for Semi-Supervised Visible-Infrared Person Re-Identification
Jiangming Shi, Yachao Zhang, Xiangbo Yin, Yuan Xie, Zhizhong Zhang, Jianping Fan, Zhongchao Shi, Yanyun Qu
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 |
|---|---|---|---|
| use DPIS dual pseudo-label self-training instead of OTLA | visible-infrared ReID · SYSU-MM01 all-search, uni-semi-supervised | Rank-1: 48.2 -> 58.4 | Improved |
| apply existing unsupervised domain adaptation methods | visible-infrared ReID · SYSU-MM01 all-search, uni-semi-supervised | Rank-1: 7.3 to 15.1 Rank-1 for UDA methods | No clear effect |
| add hybrid pseudo-labels (DPI) to the visible-label baseline (ablation) | baseline · SYSU-MM01 all-search | Rank-1: 3.80 -> 36.56 | Improved |
| add NLP on top of DPI (ablation) | DPIS · SYSU-MM01 all-search | Rank-1: 36.56 -> 51.90 | Improved |
| add NCC and UAL on top of DPI and NLP (ablation) | DPIS · SYSU-MM01 all-search | Rank-1: 51.90 -> 58.40 | Improved |
| use DPIS in the bi-semi-supervised setting versus re-implemented supervised methods | visible-infrared ReID · SYSU-MM01 all-search, 10% labels | Rank-1: 37.90 -> 57.70 (vs DART) | Improved |
| compare DPIS (uni-semi-supervised) against fully supervised methods | visible-infrared ReID · SYSU-MM01 all-search | Rank-1: 58.4 vs LUPI 71.1 | Mixed |
| vary hyper-parameter tau_sam in the unreliable anchor loss from 6 to 14 (ablation) | DPIS · SYSU-MM01 all-search | Rank-1 | No clear effect |
Closest papers by meaning
- Exploring Homogeneous and Heterogeneous Consistent Label Associations for Unsupervised Visible-Infrared Person ReID (IJCV 2024 · similarity 0.91)
- Relieving Universal Label Noise for Unsupervised Visible-Infrared Person Re-Identification by Inferring from Neighbors (AAAI 2025 · similarity 0.91)
- Learning Commonality, Divergence and Variety for Unsupervised Visible-Infrared Person Re-identification (NeurIPS 2024 · similarity 0.88)
- TokenMatcher: Diverse Tokens Matching for Unsupervised Visible-Infrared Person Re-Identification (AAAI 2025 · similarity 0.88)
- Shallow-Deep Collaborative Learning for Unsupervised Visible-Infrared Person Re-Identification (CVPR 2024 · similarity 0.87)
- High-Order Structure Based Middle-Feature Learning for Visible-Infrared Person Re-identification (AAAI 2024 · similarity 0.87)
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.
