AI Paper Atlas

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

CVPR 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Cross-modality and occlusion re-identification · 333 citations (OpenAlex)

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 changedWhereMeasuredEffect
add feature-distance adversarial hard-negative generationVGGM vehicle ReID embedding model · VERI-Wild SmallmAP: 28.77 -> 35.11Improved
add feature-distance adversarial hard-negative generationVGGM vehicle ReID embedding model · VERI-Wild MediummAP: 24.63 -> 29.80Improved
add feature-distance adversarial hard-negative generationVGGM vehicle ReID embedding model · VERI-Wild LargemAP: 19.48 -> 22.78Improved
add feature-distance adversarial hard-negative generationVGGM vehicle ReID embedding model · VehicleID, Test Size=1600mAP: 55.78 -> 65.33Improved
add feature-distance adversarial hard-negative generationVGGM vehicle ReID embedding model · VehicleID, Test Size=2400mAP: 52.20 -> 61.84Improved
add feature-distance adversarial hard-negative generationVGGM vehicle ReID embedding model · VeRI-776mAP: 47.85 -> 55.49Improved
add attention regularization (ablation)FDA-Net · VERI-Wild SmallmAP: 32.40 -> 35.11Improved
add attention regularization (ablation)FDA-Net · VERI-Wild MediummAP: 27.10 -> 29.80Improved
add attention regularization (ablation)FDA-Net · VERI-Wild LargemAP: 21.13 -> 22.78Improved
add attention regularization (ablation)FDA-Net · VehicleID, Test Size=1600mAP: 62.71 -> 65.33Improved
add attention regularization (ablation)FDA-Net · VehicleID, Test Size=2400mAP: 59.26 -> 61.84Improved
add attention regularization (ablation)FDA-Net · VeRI-776mAP: 53.46 -> 55.49Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy