Research map / Label-efficient and robust learning / Recognition and long-tail
Diverse Embedding Expansion Network and Low-Light Cross-Modality Benchmark for Visible-Infrared Person Re-Identification
Read the paperCheck 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 |
|---|---|---|---|
| Add DEE to the baseline (ablation) | DEEN · LLCM | Rank-1: 45.4 -> 50.5 | Helped |
| Add CPM loss to DEE (ablation) | DEEN · LLCM | Rank-1: 50.5 -> 53.1 | Helped |
| Add orthogonal loss to DEE (ablation) | DEEN · LLCM | Rank-1: 50.5 -> 51.5 | Helped |
| Add MFA to the baseline (ablation) | DEEN · LLCM | Rank-1: 45.4 -> 51.2 | Helped |
| Add DEE, CPM, orthogonal loss, and MFA together (ablation) | DEEN · SYSU-MM01 | Rank-1: 60.7 -> 74.7 | Helped |
| Place DEE after stage-3 rather than stage-2 (ablation) | DEEN · LLCM | Rank-1: 49.6 -> 53.9 | Helped |
| Place DEE after stage-4 rather than stage-3 (ablation) | DEEN · LLCM | Rank-1: 53.9 -> 50.9 | Hurt |
| Increase DEE branches from two to three (ablation) | DEEN · LLCM | Rank-1: 52.6 -> 53.9 | Helped |
| Increase DEE branches from three to four (ablation) | DEEN · LLCM | Rank-1: 53.9 -> 52.4 | Hurt |
| Replace the Non-Local block with MFA (ablation) | DEEN without DEE · LLCM | Rank-1: 50.1 -> 51.2 | Helped |
| Replace the Non-Local block with MFA while using DEE (ablation) | DEEN · LLCM | Rank-1: 54.2 -> 54.9 | Helped |
| Use DEEN rather than MAUM | SYSU-MM01 All Search · SYSU-MM01 All Search | Rank-1: 71.7 -> 74.7 | Helped |
Closest papers by meaning
- Learning Commonality, Divergence and Variety for Unsupervised Visible-Infrared Person Re-identification (NeurIPS 2024 · similarity 0.86)
- Shallow-Deep Collaborative Learning for Unsupervised Visible-Infrared Person Re-Identification (CVPR 2024 · similarity 0.85)
- High-Order Structure Based Middle-Feature Learning for Visible-Infrared Person Re-identification (AAAI 2024 · similarity 0.85)
- TokenMatcher: Diverse Tokens Matching for Unsupervised Visible-Infrared Person Re-Identification (AAAI 2025 · similarity 0.85)
- Relieving Universal Label Noise for Unsupervised Visible-Infrared Person Re-Identification by Inferring from Neighbors (AAAI 2025 · similarity 0.85)
- Implicit Discriminative Knowledge Learning for Visible-Infrared Person Re-Identification (CVPR 2024 · similarity 0.85)
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.