Research map / Label-efficient and robust learning / Recognition and long-tail
Fine-Grained Shape-Appearance Mutual Learning for Cloth-Changing 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 FSAM instead of RGA-SC | cloth-changing Re-ID · LTCC | R-1: 31.4 -> 38.5 | Helped |
| Use FSAM instead of RGA-SC | cloth-changing Re-ID · PRCC | R-1: 42.3 -> 54.5 | Helped |
| Use FSAM instead of ISP | cloth-changing Re-ID · VC-Clothes | R-1: 72.0 -> 78.6 | Helped |
| Add logit-level mutual learning (ablation) | appearance stream · LTCC and PRCC cloth-changing | R-1: LTCC 29.8 -> 31.6; PRCC 43.7 -> 47.6 | Helped |
| Add dense similarity interaction (ablation) | FSAM with logit-level mutual learning · LTCC and PRCC cloth-changing | R-1: LTCC 31.6 -> 34.4; PRCC 47.6 -> 51.3 | Helped |
| Add parsing knowledge preservation (ablation) | FSAM · LTCC and PRCC cloth-changing | R-1: LTCC 34.4 -> 35.5; PRCC 51.3 -> 53.1 | Helped |
| Use pose-specific branches rather than a plain multi-branch structure (ablation) | shape feature extractor in FSAM · LTCC and PRCC cloth-changing | R-1: LTCC 33.9 -> 38.5; PRCC 52.3 -> 54.5 | Helped |
| Add identity guidance to mask learning (ablation) | shape stream · LTCC cloth-changing | R-1: 9.7 -> 16.3 | Helped |
| Add identity-guided shape masks to mutual learning (ablation) | FSAM · PRCC cloth-changing | R-1: 48.3 -> 54.5 | Helped |
| Use two-way rather than one-way shape-to-appearance transfer (ablation) | FSAM · PRCC cloth-changing | R-1: 52.0 -> 54.5 | Helped |
| Use shape masks rather than RGB images in the shape stream (ablation) | FSAM mutual learning · PRCC cloth-changing | R-1: 51.8 -> 54.5 | Helped |
| Use FSAM instead of the baseline | standard Re-ID · DukeMTMC | R-1: 85.5 -> 86.4 | Hurt |
Closest papers by meaning
- DIFFER: Disentangling Identity Features via Semantic Cues for Clothes-Changing Person Re-ID (CVPR 2025 · similarity 0.90)
- Identity-Clothing Similarity Modeling for Unsupervised Clothing Change Person Re-Identification (CVPR 2025 · similarity 0.87)
- SEAS: ShapE-Aligned Supervision for Person Re-Identification (CVPR 2024 · similarity 0.87)
- Distilling CLIP with Dual Guidance for Learning Discriminative Human Body Shape Representation (CVPR 2024 · similarity 0.86)
- DKC: Differentiated Knowledge Consolidation for Cloth-Hybrid Lifelong Person Re-identification (CVPR 2025 · similarity 0.86)
- From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization (CVPR 2025 · similarity 0.84)
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.