Research map / Label-efficient and robust learning / Recognition and long-tail
Learning to Reduce Dual-Level Discrepancy for Infrared-Visible Person Re-Identification
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 dual-level image translation and feature embedding instead of feature-level constraints alone | IV-REID · RegDB | CMC-1: 33.47 -> 43.4 | Helped |
| use dual-level image translation and feature embedding instead of feature-level constraints alone | IV-REID · SYSU-MM01 | CMC-1: 26.97 -> 28.9 | Helped |
| add VAE-based modality disentanglement (ablation) | D2RL · RegDB | CMC-1: 34.8 -> 43.4 | Helped |
| add cycle-consistency loss for modality transfer (ablation) | D2RL · RegDB | CMC-1: 33.7 -> 43.4 | Helped |
| add cross-entropy loss (ablation) | D2RL · RegDB | CMC-1: 41.7 -> 43.4 | Helped |
| add triplet loss (ablation) | D2RL · RegDB | CMC-1: 39.5 -> 43.4 | Helped |
| add image-level modality unification (ablation) | TF-only baseline · RegDB | CMC-1: 28.5 -> 43.4 | Helped |
| unify images to multi-spectral rather than visible modality (ablation) | D2RL · RegDB | CMC-1: 39.1 -> 43.4 | Helped |
| unify images to multi-spectral rather than infrared modality (ablation) | D2RL · RegDB | CMC-1: 42.9 -> 43.4 | Helped |
| unify images to multi-spectral rather than visible modality (ablation) | D2RL · SYSU-MM01 | CMC-1: 28.1 -> 28.9 | Helped |
| unify images to multi-spectral rather than infrared modality (ablation) | D2RL · SYSU-MM01 | CMC-1: 27.4 -> 28.9 | Helped |
| train image-level and feature-level subnetworks jointly instead of separately (ablation) | D2RL · RegDB | CMC-1: 39.9 -> 43.4 | Helped |
Closest papers by meaning
- High-Order Structure Based Middle-Feature Learning for Visible-Infrared Person Re-identification (AAAI 2024 · similarity 0.90)
- Learning Commonality, Divergence and Variety for Unsupervised Visible-Infrared Person Re-identification (NeurIPS 2024 · similarity 0.90)
- Implicit Discriminative Knowledge Learning for Visible-Infrared Person Re-Identification (CVPR 2024 · similarity 0.90)
- Shallow-Deep Collaborative Learning for Unsupervised Visible-Infrared Person Re-Identification (CVPR 2024 · similarity 0.89)
- TokenMatcher: Diverse Tokens Matching for Unsupervised Visible-Infrared Person Re-Identification (AAAI 2025 · similarity 0.88)
- Relieving Universal Label Noise for Unsupervised Visible-Infrared Person Re-Identification by Inferring from Neighbors (AAAI 2025 · similarity 0.88)
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.