Research map / Label-efficient and robust learning / Recognition and long-tail
Visible-Infrared Person Re-Identification via Semantic Alignment and Affinity Inference
Xingye Fang, Yang Yang, Ying Fu
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 semantic-aligned feature learning (SAFL) (ablation) | ResNet-50 baseline · SYSU-MM01 all-search single-shot | mAP (%): 61.59 -> 71.69 | Improved |
| add affinity inference module (AIM) (ablation) | ResNet-50 baseline · SYSU-MM01 all-search single-shot | mAP (%): 61.59 -> 67.78 | Improved |
| add center separation loss (ablation) | SAAI · SYSU-MM01 all-search single-shot | mAP (%): 72.15 -> 76.12 | Improved |
| add part diversity loss (ablation) | SAAI · SYSU-MM01 all-search single-shot | mAP (%): 72.15 -> 72.54 | Improved |
| add noise removal step in AIM (ablation) | AIM · SYSU-MM01 indoor-search single-shot | mAP (%): 67.69 -> 79.67 | Improved |
| add mean expansion step in AIM (ablation) | AIM · SYSU-MM01 indoor-search single-shot | mAP (%): 79.67 -> 82.39 | Improved |
| add AIM to MPANet at inference | MPANet (retrained) · SYSU-MM01 all-search multi-shot | mAP (%): 62.92 -> 78.27 | Improved |
| add AIM to AGW at inference | AGW (retrained) · SYSU-MM01 all-search multi-shot | mAP (%): 41.48 -> 55.18 | Improved |
| increase learnable prototypes beyond 7 (ablation) | SAFL · SYSU-MM01 all-search single-shot | mAP (%): 77.03 -> 77.01 (p=9), 76.51 (p=11) | Hurt |
| SAAI versus best prior on RegDB Visible2Infrared | SAAI · RegDB Visible2Infrared | Rank-1 (%): 95.17 -> 91.07 | Hurt |
Closest papers by meaning
- Learning by Aligning: Visible-Infrared Person Re-Identification Using Cross-Modal Correspondences (ICCV 2021 · similarity 0.92)
- Implicit Discriminative Knowledge Learning for Visible-Infrared Person Re-Identification (CVPR 2024 · similarity 0.90)
- Empowering Visible-Infrared Person Re-Identification with Large Foundation Models (NeurIPS 2024 · similarity 0.90)
- High-Order Structure Based Middle-Feature Learning for Visible-Infrared Person Re-identification (AAAI 2024 · similarity 0.90)
- TokenMatcher: Diverse Tokens Matching for Unsupervised Visible-Infrared Person Re-Identification (AAAI 2025 · similarity 0.89)
- Learning Commonality, Divergence and Variety for Unsupervised Visible-Infrared Person Re-identification (NeurIPS 2024 · similarity 0.89)
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.
