Research map / Label-efficient and robust learning / Recognition and long-tail
Learning Coarse-to-Fine Structured Feature Embedding for Vehicle 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 coarse-grained ranking loss (ablation) | FGR · VehicleID Small | top-1 match rate: 0.502 -> 0.589 | Helped |
| add pairwise loss (ablation) | C+FGR · VehicleID Small | top-1 match rate: 0.589 -> 0.598 | Helped |
| add vehicle model classification loss (ablation) | C+FGR+P · VehicleID Small | top-1 match rate: 0.598 -> 0.611 | Helped |
| add vehicle model classification loss (ablation) | C+FGR+P · VehicleID Small | MAP: 0.625 -> 0.635 | Helped |
| add coarse-grained ranking loss (ablation) | FGR · Vehicle-1M Small | MAP: 0.825 -> 0.852 | Helped |
| add pairwise loss (ablation) | C+FGR · Vehicle-1M Small | MAP: 0.852 -> 0.866 | Helped |
| add vehicle model classification loss (ablation) | C+FGR+P · Vehicle-1M Small | top-1 match rate: 0.667 -> 0.671 | Helped |
| fine-grained ranking loss instead of classification-trained features (ablation) | GoogLeNet · Vehicle-1M Small | top-1 match rate: 0.545 -> 0.634 | Helped |
| C2F-Rank loss instead of coupled clusters loss (DRDL) | GoogLeNet · VehicleID Small | top-1 match rate: 0.49 -> 0.611 | Helped |
| vary alpha 50-500 and gamma 5-50 (ablation) | C2F-Rank · VehicleID and Vehicle-1M | match rate | No clear effect |
Closest papers by meaning
- Parsing-Based View-Aware Embedding Network for Vehicle Re-Identification (CVPR 2020 · similarity 0.90)
- Part-Regularized Near-Duplicate Vehicle Re-Identification (CVPR 2019 · similarity 0.90)
- Infer the Whole from a Glimpse of a Part: Keypoint-Based Knowledge Graph for Vehicle Re-Identification (AAAI 2025 · similarity 0.87)
- CLIP-driven View-aware Prompt Learning for Unsupervised Vehicle Re-identification (AAAI 2025 · similarity 0.87)
- Alice Benchmarks: Connecting Real World Re-Identification with the Synthetic (ICLR 2024 · similarity 0.84)
- Structural Information Guided Multimodal Pre-training for Vehicle-Centric Perception (AAAI 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.