Research map / Label-efficient and robust learning / Recognition and long-tail
PartMix: Regularization Strategy To Learn Part Discovery 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 PartMix to MPANet | MPANet · SYSU-MM01 all-search single-shot | mAP: 68.24 -> 74.62 | Helped |
| add PartMix to MPANet | MPANet · SYSU-MM01 all-search multi-shot | mAP: 62.91 -> 69.84 | Helped |
| add PartMix to MPANet | MPANet · SYSU-MM01 indoor-search single-shot | Rank-1: 76.74 -> 81.52 | Helped |
| add PartMix to MPANet | MPANet · RegDB infrared to visible | mAP: 80.7 -> 82.52 | Helped |
| add intra-modality part mixing (ablation) | MPANet baseline · SYSU-MM01 single-shot | Rank-1: 70.58 -> 72.72 | Helped |
| add inter-modality part mixing (ablation) | MPANet baseline · SYSU-MM01 single-shot | Rank-1: 70.58 -> 75.61 | Helped |
| add entropy-based mining (ablation) | MPANet with intra- and inter-modality part mixing · SYSU-MM01 single-shot | Rank-1: 75.86 -> 77.78 | Helped |
| apply image-level MixUp (ablation) | MPANet baseline · SYSU-MM01 single-shot | Rank-1: 70.58 -> 51.48 | Hurt |
| apply Manifold MixUp (ablation) | MPANet baseline · SYSU-MM01 single-shot | Rank-1: 70.58 -> 71.25 | Helped |
| apply Manifold MixUp (ablation) | MPANet baseline · SYSU-MM01 single-shot | mAP: 68.24 -> 67.74 | Hurt |
| apply image-level CutMix (ablation) | MPANet baseline · SYSU-MM01 single-shot | Rank-1: 70.58 -> 73.35 | Helped |
| increase the number of mixed parts from 1 to 2 (ablation) | PartMix · SYSU-MM01 and RegDB | performance | Helped |
Closest papers by meaning
- Learning Commonality, Divergence and Variety for Unsupervised Visible-Infrared Person Re-identification (NeurIPS 2024 · similarity 0.87)
- High-Order Structure Based Middle-Feature Learning for Visible-Infrared Person Re-identification (AAAI 2024 · similarity 0.86)
- Diffusion-based Synthetic Data Generation for Visible-Infrared Person Re-Identification (AAAI 2025 · similarity 0.85)
- Empowering Visible-Infrared Person Re-Identification with Large Foundation Models (NeurIPS 2024 · similarity 0.84)
- Relieving Universal Label Noise for Unsupervised Visible-Infrared Person Re-Identification by Inferring from Neighbors (AAAI 2025 · similarity 0.84)
- Shallow-Deep Collaborative Learning for Unsupervised Visible-Infrared Person Re-Identification (CVPR 2024 · similarity 0.83)
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.