Research map / Label-efficient and robust learning / Recognition and long-tail
Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared 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 hierarchical cross-modality disentanglement with ID-PIG and HFL | VI-ReID · RegDB | Rank-1: 50.85 -> 70.93 | Helped |
| Use hierarchical cross-modality disentanglement with ID-PIG and HFL | VI-ReID · SYSU-MM01 | Rank-1: 28.90 -> 34.94 | Helped |
| Add alternate sampling of original and cross-reconstructed features (ablation) | HFL with CE+TRIP and A+P features · RegDB | Rank-1: 53.25 -> 70.93 | Helped |
| Add alternate sampling of original and cross-reconstructed features (ablation) | HFL with CE+TRIP and A+P features · SYSU-MM01 | mAP: 30.53 -> 35.94 | Helped |
| Combine style-attribute and prototype codes rather than using style-attribute code alone (ablation) | HFL on original images with CE+TRIP · RegDB | Rank-1: 15.33 -> 53.25 | Helped |
| Combine style-attribute and prototype codes rather than using prototype code alone (ablation) | HFL on original images with CE+TRIP · SYSU-MM01 | Rank-1: 22.51 -> 29.19 | Helped |
| Remove same-modality reconstruction loss (ablation) | ID-PIG · RegDB and SYSU-MM01 image translation | visual image quality | Hurt |
| Remove cross-modality reconstruction loss (ablation) | ID-PIG · RegDB and SYSU-MM01 image translation | visual image quality | Hurt |
| Remove adversarial loss (ablation) | ID-PIG · RegDB and SYSU-MM01 image translation | visual image quality | Hurt |
Closest papers by meaning
- Cross-Modality Person Re-identification with Memory-Based Contrastive Embedding (AAAI 2023 · similarity 0.92)
- Hierarchical Discriminative Learning for Visible Thermal Person Re-Identification (AAAI 2018 · similarity 0.92)
- Shallow-Deep Collaborative Learning for Unsupervised Visible-Infrared Person Re-Identification (CVPR 2024 · similarity 0.90)
- TokenMatcher: Diverse Tokens Matching for Unsupervised Visible-Infrared Person Re-Identification (AAAI 2025 · similarity 0.90)
- Implicit Discriminative Knowledge Learning for Visible-Infrared Person Re-Identification (CVPR 2024 · similarity 0.90)
- High-Order Structure Based Middle-Feature Learning for Visible-Infrared Person Re-identification (AAAI 2024 · 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.