Research map / Label-efficient and robust learning / Recognition and long-tail
Joint Color-irrelevant Consistency Learning and Identity-aware Modality Adaptation for Visible-infrared Cross Modality 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 color-irrelevant consistency learning (CICL) (ablation) | CIMA baseline · SYSU-MM01 | mAP: 46.7 -> 54.8 | Helped |
| Add color-irrelevant consistency learning (CICL) (ablation) | CIMA baseline · RegDB | mAP: 51.8 -> 60.1 | Helped |
| Add identity-aware modality adaptation (IAMA) (ablation) | CIMA baseline · RegDB | Rank-1: 52.3 -> 70.0 | Helped |
| Add CICL and IAMA together (ablation) | CIMA baseline · SYSU-MM01 | mAP: 46.7 -> 59.3 | Helped |
| Add CICL and IAMA together (ablation) | CIMA baseline · RegDB | mAP: 51.8 -> 69.4 | Helped |
| Use intra-modality CICL only (ablation) | CIMA baseline · SYSU-MM01 | Rank-1: 45.3 -> 51.4 | Helped |
| Use inter-modality CICL only (ablation) | CIMA baseline · SYSU-MM01 | Rank-1: 45.3 -> 49.2 | Helped |
| Add inter-modality CICL alongside intra-modality CICL (ablation) | CIMA baseline · SYSU-MM01 | mAP: 51.9 -> 54.8 | Helped |
| Add feature embedding consistency to identity prediction consistency (ablation) | CICL · SYSU-MM01 | mAP: 49.6 -> 52.3 | Helped |
| Add probability distribution consistency to prediction and feature embedding consistency (ablation) | CICL · SYSU-MM01 | mAP: 52.3 -> 54.8 | Helped |
| Use grayscale images instead of CICL's clothing color transformation (ablation) | CIMA baseline · RegDB | Rank-1: 62.1 -> 55.8 | Hurt |
| Use naive color augmentation instead of CICL (ablation) | CIMA baseline · RegDB | mAP: 60.1 -> 56.2 | Hurt |
Closest papers by meaning
- Cross-Modality Person Re-identification with Memory-Based Contrastive Embedding (AAAI 2023 · similarity 0.92)
- Infrared-Visible Cross-Modal Person Re-Identification with an X Modality (AAAI 2020 · similarity 0.92)
- Implicit Discriminative Knowledge Learning for Visible-Infrared Person Re-Identification (CVPR 2024 · similarity 0.91)
- Empowering Visible-Infrared Person Re-Identification with Large Foundation Models (NeurIPS 2024 · similarity 0.90)
- Cross-Modality Perturbation Synergy Attack for Person Re-identification (NeurIPS 2024 · similarity 0.90)
- Shallow-Deep Collaborative Learning for Unsupervised Visible-Infrared Person Re-Identification (CVPR 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.