Research map / Label-efficient and robust learning / Recognition and long-tail
VERI-Wild: A Large Dataset and a New Method for Vehicle Re-Identification in the Wild
Yihang Lou, Yan Bai, Jun Liu, Shiqi Wang, Lingyu Duan
Check 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 feature-distance adversarial hard-negative generation | VGGM vehicle ReID embedding model · VERI-Wild Small | mAP: 28.77 -> 35.11 | Improved |
| add feature-distance adversarial hard-negative generation | VGGM vehicle ReID embedding model · VERI-Wild Medium | mAP: 24.63 -> 29.80 | Improved |
| add feature-distance adversarial hard-negative generation | VGGM vehicle ReID embedding model · VERI-Wild Large | mAP: 19.48 -> 22.78 | Improved |
| add feature-distance adversarial hard-negative generation | VGGM vehicle ReID embedding model · VehicleID, Test Size=1600 | mAP: 55.78 -> 65.33 | Improved |
| add feature-distance adversarial hard-negative generation | VGGM vehicle ReID embedding model · VehicleID, Test Size=2400 | mAP: 52.20 -> 61.84 | Improved |
| add feature-distance adversarial hard-negative generation | VGGM vehicle ReID embedding model · VeRI-776 | mAP: 47.85 -> 55.49 | Improved |
| add attention regularization (ablation) | FDA-Net · VERI-Wild Small | mAP: 32.40 -> 35.11 | Improved |
| add attention regularization (ablation) | FDA-Net · VERI-Wild Medium | mAP: 27.10 -> 29.80 | Improved |
| add attention regularization (ablation) | FDA-Net · VERI-Wild Large | mAP: 21.13 -> 22.78 | Improved |
| add attention regularization (ablation) | FDA-Net · VehicleID, Test Size=1600 | mAP: 62.71 -> 65.33 | Improved |
| add attention regularization (ablation) | FDA-Net · VehicleID, Test Size=2400 | mAP: 59.26 -> 61.84 | Improved |
| add attention regularization (ablation) | FDA-Net · VeRI-776 | mAP: 53.46 -> 55.49 | Improved |
Closest papers by meaning
- Disentangled Feature Learning Network and a Comprehensive Benchmark for Vehicle Re-Identification (TPAMI 2021 · similarity 0.93)
- Vehicle Re-Identification in Aerial Imagery: Dataset and Approach (ICCV 2019 · similarity 0.87)
- RVSL: Robust Vehicle Similarity Learning in Real Hazy Scenes Based on Semi-Supervised Learning (ECCV 2022 · similarity 0.87)
- Viewpoint-Aware Attentive Multi-View Inference for Vehicle Re-Identification (CVPR 2018 · similarity 0.86)
- Day-Night Cross-domain Vehicle Re-identification (CVPR 2024 · similarity 0.85)
- Alice Benchmarks: Connecting Real World Re-Identification with the Synthetic (ICLR 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.
