Research map / Label-efficient and robust learning / Recognition and long-tail
Towards Grand Unified Representation Learning for Unsupervised Visible-Infrared Person Re-Identification
Bin Yang, Jun Chen, Mang Ye
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 cross-memory association embedding (CAE) to bottom-up domain learning (ablation) | GUR · SYSU-MM01 (all search) | Rank-1: 36.63 -> 55.96 | Improved |
| add bottom-up domain learning alone to ADC baseline (ablation) | ADC baseline · SYSU-MM01 (all search) | Rank-1: 35.07 -> 36.63 | No clear effect |
| add cross-modality label unification (CLU) on top of BD+CAE (ablation) | GUR · SYSU-MM01 (all search) | Rank-1: 55.96 -> 63.51 | Improved |
| add bottom-up domain learning to CAE + CLU (ablation) | GUR · RegDB (visible to infrared) | Rank-1: 62.82 -> 73.91 | Improved |
| add cross-modality label unification (CLU) (ablation) | GUR · RegDB (visible to infrared) | Rank-1: 69.13 -> 73.91 | Improved |
| set CAE temperature sigma to 0.05 (below 1.0) (ablation) | GUR · SYSU-MM01 | Rank-1 | Improved |
| use camera labels in training (ablation) | GUR · SYSU-MM01 (all search) | Rank-1: 60.95 -> 63.51 | Improved |
Closest papers by meaning
- Exploring Homogeneous and Heterogeneous Consistent Label Associations for Unsupervised Visible-Infrared Person ReID (IJCV 2024 · similarity 0.94)
- Shallow-Deep Collaborative Learning for Unsupervised Visible-Infrared Person Re-Identification (CVPR 2024 · similarity 0.93)
- Relieving Universal Label Noise for Unsupervised Visible-Infrared Person Re-Identification by Inferring from Neighbors (AAAI 2025 · similarity 0.92)
- Implicit Discriminative Knowledge Learning for Visible-Infrared Person Re-Identification (CVPR 2024 · similarity 0.92)
- Empowering Visible-Infrared Person Re-Identification with Large Foundation Models (NeurIPS 2024 · similarity 0.91)
- TokenMatcher: Diverse Tokens Matching for Unsupervised Visible-Infrared Person Re-Identification (AAAI 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.
