Research map / Label-efficient and robust learning / Recognition and long-tail
Unstructured Feature Decoupling for Vehicle Re-identification
Wen Qian, Hao Luo, Silong Peng, Fan Wang, Chen Chen, Hao Li
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 transformer-based decomposing head (TDH) (ablation) | ResNet50 baseline · VeRi-776 | mAP: 79.6 -> 81.0 | Improved |
| add transformer-based decomposing head (TDH) (ablation) | Swin-Tiny baseline · VeRi-776 | mAP: 78.2 -> 80.0 | Improved |
| add cluster-based decoupling constraint (CDC) on top of TDH (ablation) | UFDN Res50 · VeRi-776 | mAP: 81.0 -> 81.5 | Improved |
| add cluster-based decoupling constraint (CDC) on top of TDH (ablation) | UFDN Swin-Tiny · VeRi-776 | mAP: 80.0 -> 80.9 | Improved |
| add diversity constraint (ablation) | UFDN Res50 · VeRi-776 | mAP: 81.0 -> 81.2 | Improved |
| add plain alignment constraint to diversity constraint (ablation) | UFDN Swin-Tiny · VeRi-776 | mAP: 80.5 -> 80.3 | Hurt |
| use modulated alignment constraint instead of plain one, with diversity (ablation) | UFDN Res50 · VeRi-776 | mAP: 81.2 -> 81.5 | Improved |
| use modulated alignment constraint instead of plain one, with diversity (ablation) | UFDN Swin-Tiny · VeRi-776 | mAP: 80.3 -> 80.9 | Improved |
| set TDH depth to 2 instead of 1 or 4 (ablation) | UFDN Res50 · VehicleID | CMC@1: 86.5 -> 88.4 | Improved |
| set TDH depth to 2 instead of 4 (ablation) | UFDN Res50 · VehicleID | CMC@1: 85.2 -> 88.4 | Improved |
| decouple into four parts instead of one (ablation) | UFDN Res50 · VehicleID | CMC@1: 86.5 -> 88.4 | Improved |
| use 16 decoupled parts instead of 4 (ablation) | UFDN Res50 · VeRi-776 | mAP: 81.5 -> 80.3 | Hurt |
Closest papers by meaning
- Disentangled Feature Learning Network and a Comprehensive Benchmark for Vehicle Re-Identification (TPAMI 2021 · similarity 0.89)
- Part-Regularized Near-Duplicate Vehicle Re-Identification (CVPR 2019 · similarity 0.87)
- Learning Coarse-to-Fine Structured Feature Embedding for Vehicle Re-Identification (AAAI 2018 · similarity 0.86)
- Infer the Whole from a Glimpse of a Part: Keypoint-Based Knowledge Graph for Vehicle Re-Identification (AAAI 2025 · similarity 0.85)
- CLIP-driven View-aware Prompt Learning for Unsupervised Vehicle Re-identification (AAAI 2025 · similarity 0.84)
- DeMo: Decoupled Feature-Based Mixture of Experts for Multi-Modal Object Re-Identification (AAAI 2025 · 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.
